If you&#x27;re seeing this message, that means JavaScript has been disabled on your browser · Please enable JavaScript to make this website work

Tech in Asia - Connecting Asia's startup ecosystem

Fintech startup BharatX acquires healthcare finance firm Zenifi to enter medical lending. Zenifi CEO Padam Kataria joins BharatX to lead healthcare lending vertical.

BharatX: BharatX expands into healthcare finance with acquisition of Zenifi - The Economic Times

Bharat Electronics Limited (BEL) is an Indian Government-owned aerospace and defence electronics company. It primarily manufactures advanced electronic products for ground and aerospace applications. BEL is one of sixteen PSUs under the Ministry of Defence of India.

Bharat Electronics - Wikipedia

Bharat Petroleum is among the leading oil and gas companies in India. The organisation aims to provide only the purest oil in India by virtue of using its own highly developed refineries.

Oil & Gas Companies in India |Top Petroleum Companies | Petroleum ...

BHEL is one of the largest engineering and manufacturing companies of its kind in India engaged in design, engineering, construction, testing, commissioning and servicing of a wide range of products and services with over 180 product offerings to meet the ever-growing needs of the core sectors ...

Official Website of Bharat Heavy Electricals Limited, New Delhi, ...

Bharat Forge is one of the leading forging companies in India. A preferred technology and engineering driven development partner and global leader in metal forming, Bharat Forge serves several sectors including Automotive, Railways, Aerospace, Marine, Oil and Gas, Power, Construction and Mining.

Bharat Forge - One of the Leading Forging Companies in India

भारत सरकार GOVERNMENT OF INDIA · A Govt of India Enterprise, Ministry of Defence

Home Page | BHARAT DYNAMICS LIMITED INDIA

BharatX | 36,417 followers on LinkedIn. Redefining Credit for the Indian Middle Class. | BharatX is a VC Backed early-stage FinTech startup that uses technology to empower the Indian Middle Class with credit. Approximately 110 Million Households whose income is more than 5 lakh per annum, do ...

BharatX | LinkedIn

Fintech startup BharatX has raised $4.5 million in a funding round from Silicon Valley-based famed accelerator Y Combinator, 8i Ventures, Multiply Ventures and Soma Capital. The company plans to utilise the funds to expand its team and develop its product.

BharatX Funding: Fintech startup BharatX raises $4.5 million in ...

The funding will help drive BharatX&#x27;s delivery of seamless Embedded Credit experiences on many consumer-facing platforms, with zero credit risk and zero operational headaches for the platforms

Fintech firm BharatX raises $250,000 in pre-seed round led by Java ...

BharatX

bharatx

The Binance Build for Bharat hackathon - by , the global blockchain company behind the world’s largest digital asset exchange and blockchain protocol - Binance Smart Chain, announced Semiott Protocol, and as the top three winners. This was the first DeFi-focused Hackathon in India, based on the vision of the initiative - : an initiative designed under the . The Hackathon also gained the support of large scale tech players: ( Previously Matic Network ), , , . Binance Whrrl GoSats Polaris Accelerator Programme Blockchain for India Fund Google Cloud, Polygon Marlin Protocol Band Protocol Ankr cloud infrastructure The winners were selected from a pool of 350+ developers and startups that had applied for the Build for Bharat programme and were challenged with multiple tasks including a 48 hours long hackathon and Binance Smart Chain integrations. The top 8 finalists battled it out at a virtual Demo Day with participants attending from across the globe. The event also saw an opening address by Changpeng Zhao, CEO, Binance and a panel discussion featuring Nischal Shetty, CEO, WazirX , Ryan Fang, Coo and Co-Founder, Ankr, Pratik Reddy, Head of Research at Marlin Protocol and Raghu Mohan, CEO, Lumos labs. The winner of the Hackathon, the Semiott Protocol by , a serial entrepreneur, is an algorithmic stablecoin for value veracity. , the first runners up, is a blockchain platform connecting custodian of assets (warehouse) and banks with integrated commodity trading platforms. Gokul Alex Whrrl , the second runners-up, is a Bitcoin stacking app that lets users earn bitcoin rewards when they shop with partnered merchants. GoSats The Top 3 winning projects will secure prizes from a pool of 40,000 USD that includes Google Cloud Credits. “This hackathon has been an interesting and enriching experience. We are happy to provide the catalyst for the growth of the DeFi economy in India.” said Changpeng Zhao (CZ), CEO at Binance. “The disruptive projects and ideas that we have seen through this engagement has been a testimony to India’s readiness for a decentralized economy and at Binance we are happy to provide the necessary fuel to augment this innovation.” he added. Build for Bharat aimed to identify creators, innovators, startups, and developers from all over India working on unique and creative products utilizing digital assets and blockchain technology around decentralised finance (DeFi) such as mini-Tokens, micro financing products, blockchain datasets, blockchain-AI solutions and more. Additionally, this month Binance launched the under the $100M fund set up to connect DeFi and CeFi. The program aims to help BSC-based startups gain industry exposure and accelerate their business growth. Participants from existing hackathons, including Build for Bharat can participate in the programme. Applications for the first round of MVB Programme will close by 28th Feb. Most Valuable Builder Programme

Meet the Winners of Binance's Build for Bharat Hackathon 

Episode 17: An interview with Bharath Rao, CEO and founder of CryptoDisrupted http://LEVERJ.io Trent interviews Bharath Rao, CEO of . In the interview we discuss decentralized exchanges, derivatives trading, the 2008 market crash, and the future of crypto trading. http://LEVERJ.io Also . available on iTunes For more episodes of , or . Crypto Disrupted subscribe on YouTube subscribe and listen on iTunes

Decentralized Leveraged Exchange with Bharath Rao

Uni-OVSeg: A Step Towards Efficient and Bias-Resilient Vision Systems

India Draws International Business from Europe While Expanding into Asia and the US

Efficient Detection of Defects in Magnetic Labyrinthine Patterns: Conclusion and References

This July, India was the center of crypto media attention. This is due to two reasons: the WazirX $230 million hack and new movements in the local crypto regulation landscape. But the basic thesis of why India is important for the global crypto landscape is much simpler. With more than 1.4 billion citizens, India is the country with the biggest population, where crypto regulation and rules for VASPs already exist. There are different numbers describing the number of crypto users in India. KuCoin estimates the number of crypto users in the country at 115 million in 2022 and Tripple A at 97.5 million. Unlike China, India has crypto regulations, which makes crypto exchange legal in the country. Announced upgrades of local regulations may influence the global crypto industry. WazirX hack Unauthorized criminals hacked the multisig wallet belonging to the biggest local exchange, WazirX, on July 18th. The stolen $230 million amounted to approximately 45% of WazirX's reserves. $100 million of it was in Shiba Inu, and $52 mln was in Ethereum. Short notice about the hack was published in the company’s blog. This demonstrates a lack of security in WazirX's tech infrastructure or its crypto custody provider, Liminal. Both sides were quick to blame each other, which seems strange, considering WazirX is the most well-known crypto exchange in India. This occasion also proves that local crypto regulations need to be developed. For instance, in South Korea, such a hack will be impossible - based on local legislation crypto exchanges should store their funds not multisig, but cold wallets. As for the hack itself, it has been linked to hackers from North Korea, according to Elliptic’s investigation. Regulation Updates Bharat Web3 Association (BWA) proposed an initiative to reduce TDS tax from 1% to 0,01%. Despite that this month the Indian government has remained TDS unchanged. This came to light after the publication of the budget with the new composition of the Narendra Modi government. Also this month Economic Affairs Secretary Ajay Seth announced new crypto regulation guidelines.  Based on his speech cryptocurrencies in India are “regulated from the perspective of AML alone”. The secretary claims that “it cannot be beyond that” and the new “policy stance will come out in the discussion paper”. According to his assumption the final document will be published in September. Co-founder of another local crypto exchange CoinDCX Sumit Gupta has appreciated this initiative and сalled the government to work together on the topic. Current Regulation Approach According to local AML/CFT rules crypto entities need to register as Virtual Digital Asset Providers (VDA). Based on press release issued by Finance Ministry 28 entities were registered as VDA providers in the end of 2023 by the local Financial Intelligence Unit. These companies include Binance, Coin DCX, WazirX (Zanmai Labs), Coinswitch and Zebpay. Also the country has taxation procedures for crypto gains - CGT tax (30%) and TDS (1%) for every transaction regardless of its economic profit (or loss). If we talk about the other regulators, the RBI (Indian Central Bank) has probably the most damaging approach towards crypto and marks them as a threat to financial stability. At the same time, the SEBI (local SEC) is also implementing a number of initiatives to legalize crypto trading in the country. What can change? It looks like current issues of crypto regulations in India such as high taxation and WazirX hack, may be compared to the state of crypto regulations in Japan and South Korea several years ago. These countries also had a series of hacks that forced regulators to tighten their approach to funds storage. Also, Japan had a high taxation for crypto entities and individuals, but now it's changing its regulation approach. As I think development of crypto regulations in India may go by the same scenario like in Japan in the field of taxation and customer security. Although India has regulations for crypto exchange, it doesn't have clear regulations for some other type of VASPs including investment activity and crypto derivatives (such as ETFs). May be next year operations with crypto for investment companies will be included in the new crypto regulation framework. This is quite possible based on the current SEBI's approach. Also, no crypto cards are currently issued in India. Based on the RBI's current position, crypto cards may be referred as a threat to financial stability, because they allow crypto payments. It's different in the US and European Union. Crypto card issuers can operate there, and this market is transparent for regulators, business, and customers. Legalizing crypto cards and ETFs in India may take more time than next year. However, in the medium term (next year), the country will likely adopt proper guidelines and licensing procedures for exchanges, custodians, and crypto funds. Conclusion India is now almost as big in crypto as China and one of the fastest growing economies on the planet. So, we will continue to watch closely how the rules for crypto business are changing there. Despite the existing challenges, this jurisdiction has great potential. If you are interested in getting more crypto regulation insights, you can watch the global crypto regulation ratinghere and get updates on my Telegram channel. This July, India was the center of crypto media attention. This is due to two reasons: the WazirX $230 million hack and new movements in the local crypto regulation landscape. But the basic thesis of why India is important for the global crypto landscape is much simpler. With more than 1.4 billion citizens, India is the country with the biggest population, where crypto regulation and rules for VASPs already exist. There are different numbers describing the number of crypto users in India. KuCoin estimates the number of crypto users in the country at 115 million in 2022 and Tripple A at 97.5 million. Unlike China, India has crypto regulations, which makes crypto exchange legal in the country. Announced upgrades of local regulations may influence the global crypto industry. WazirX hack WazirX hack Unauthorized criminals hacked the multisig wallet belonging to the biggest local exchange, WazirX, on July 18th. The stolen $230 million amounted to approximately 45% of WazirX's reserves. $100 million of it was in Shiba Inu, and $52 mln was in Ethereum. Short notice about the hack was published in the company’s blog . company’s blog company’s blog This demonstrates a lack of security in WazirX's tech infrastructure or its crypto custody provider, Liminal. Both sides were quick to blame each other, which seems strange, considering WazirX is the most well-known crypto exchange in India. This occasion also proves that local crypto regulations need to be developed. For instance, in South Korea, such a hack will be impossible - based on local legislation crypto exchanges should store their funds not multisig, but cold wallets. As for the hack itself, it has been linked to hackers from North Korea, according to Elliptic’s investigation . Elliptic’s investigation Elliptic’s investigation Regulation Updates Regulation Updates Bharat Web3 Association (BWA) proposed an initiative to reduce TDS tax from 1% to 0,01%. Despite that this month the Indian government has remained TDS unchanged. This came to light after the publication of the budget with the new composition of the Narendra Modi government. remained remained Also this month Economic Affairs Secretary Ajay Seth announced new crypto regulation guidelines.  Based on his speech cryptocurrencies in India are “regulated from the perspective of AML alone”. The secretary claims that “it cannot be beyond that” and the new “policy stance will come out in the discussion paper”. According to his assumption the final document will be published in September. Co-founder of another local crypto exchange CoinDCX Sumit Gupta has appreciated this initiative and сalled the government to work together on the topic. announced Current Regulation Approach Current Regulation Approach According to local AML/CFT rules crypto entities need to register as Virtual Digital Asset Providers (VDA). Based on press release issued by Finance Ministry 28 entities were registered as VDA providers in the end of 2023 by the local Financial Intelligence Unit. These companies include Binance, Coin DCX, WazirX (Zanmai Labs), Coinswitch and Zebpay. registered Also the country has taxation procedures for crypto gains - CGT tax (30%) and TDS (1%) for every transaction regardless of its economic profit (or loss). If we talk about the other regulators, the RBI (Indian Central Bank) has probably the most damaging approach towards crypto and marks them as a threat to financial stability. At the same time, the SEBI (local SEC) is also implementing a number of initiatives to legalize crypto trading in the country. What can change? What can change? It looks like current issues of crypto regulations in India such as high taxation and WazirX hack, may be compared to the state of crypto regulations in Japan and South Korea several years ago. These countries also had a series of hacks that forced regulators to tighten their approach to funds storage. Also, Japan had a high taxation for crypto entities and individuals, but now it's changing its regulation approach. As I think development of crypto regulations in India may go by the same scenario like in Japan in the field of taxation and customer security. Although India has regulations for crypto exchange, it doesn't have clear regulations for some other type of VASPs including investment activity and crypto derivatives (such as ETFs). May be next year operations with crypto for investment companies will be included in the new crypto regulation framework. This is quite possible based on the current SEBI's approach. Also, no crypto cards are currently issued in India. Based on the RBI's current position, crypto cards may be referred as a threat to financial stability, because they allow crypto payments. It's different in the US and European Union. Crypto card issuers can operate there, and this market is transparent for regulators, business, and customers. Legalizing crypto cards and ETFs in India may take more time than next year. However, in the medium term (next year), the country will likely adopt proper guidelines and licensing procedures for exchanges, custodians, and crypto funds. Conclusion India is now almost as big in crypto as China and one of the fastest growing economies on the planet. So, we will continue to watch closely how the rules for crypto business are changing there. Despite the existing challenges, this jurisdiction has great potential. If you are interested in getting more crypto regulation insights, you can watch the global crypto regulation rating here and get updates on my Telegram channel . here Telegram channel

India: the Biggest Crypto Market Enables New Regulations Soon

ভারত: সবচেয়ে বড় ক্রিপ্টো বাজার শীঘ্রই নতুন নিয়ম চালু করে

Indien: Der größte Kryptomarkt ermöglicht bald neue Vorschriften

India: el mercado criptográfico más grande permitirá nuevas regulaciones pronto

Inde : le plus grand marché de la cryptographie permettra bientôt de nouvelles réglementations

भारत: सबसे बड़ा क्रिप्टो बाज़ार जल्द ही नए नियम लागू करेगा

インド：最大の暗号通貨市場がまもなく新たな規制を導入

인도: 가장 큰 암호화폐 시장이 곧 새로운 규제를 가능하게 합니다

Índia: o maior mercado cripto permite novas regulamentações em breve

Индия: крупнейший рынок криптовалют скоро введет новые правила

Hindistan: En Büyük Kripto Piyasası Yakında Yeni Düzenlemelere İzin Verecek

Ấn Độ: Thị trường tiền điện tử lớn nhất sẽ sớm cho phép các quy định mới

印度：最大的加密货币市场即将实施新法规

Large Language Models on Memory-Constrained Devices Using Flash Memory: Conclusion & Discussion

Authors:
(1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore;
(2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore;
(3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore;
(4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore;
(5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore;
(6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction II Method III Datasets IV Experiments, Acknowledgment, and References IV. EXPERIMENTS We test three model configurations on both the simulator and tank datasets. First, we implement a pose regression model based on GoogLeNet [7] as our baseline model. Secondly, we implement a model using ResNet-50 [9] to evaluate the improvement possible by use of a deeper network. ResNet allows us to have deeper networks with more free parameters, and tries to avoid the problem of overfitting by having residual connections between layers [9]. Thirdly, we implement a pose regression model using an LSTM as an intermediate layer. The results indicate that all three configurations can perform well in both simulated and tank datasets as shown in Table I. The errors are minimal and of comparable magnitude to the noise in the pose recorded by the camera sensors. Fig. 4 shows that the trajectories predicted by the models are very close to the actual trajectories in terms of both position and orientation. With the simulator dataset, which is free of noise, turbidity, light distortion, and other challenges that may be observed in real underwater settings, the ResNet-50 and LSTM-based model performed better than the baseline model. On the other hand, with the tank datasets with some distortions typical of underwater scenarios, ResNet-50 performed worse than the baseline model, whereas the LSTM model did better than baseline with dataset #1 (which mostly featured translation but almost no rotation). This suggests the ResNet-50 architecture may be slightly overfitting despite the regularization, so it is not able to provide better performance in the tank dataset. We also note that data augmentation significantly improves the model performance, so in cases where there is no significant rotation, the use of data from both cameras can be used to bolster performance. Overall, these methods are robust for application in real underwater environments, and show promise for use in open water settings, where they will be tested next. ACKNOWLEDGMENT This research project is supported by A*STAR under its RIE2020 Advanced Manufacturing and Engineering (AME) Industry Alignment Fund - Pre-Positioning (IAF-PP) Grant No. A20H8a0241. REFERENCES [1] J. Gonzalez-Garcıa, A. Gomez-Espinosa, E. Cuan-Urquizo, L. G. ´ Garcıa-Valdovinos, T. Salgado-Jimenez, and J. A. E. Cabello, “Au-tonomous Underwater Vehicles: Localization, Navigation, and Commu- nication for Collaborative Missions,” Applied Sciences, vol. 10, no. 4, p. 1256, Feb. 2020. [2] L. Peng and M. Chitre, ”Regressing Poses from Monocular Images in an Underwater Environment”, 2022 OCEANS - Chennai, in press. [3] A. Kendall, M. Grimes and R. Cipolla, ”PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization,” 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 2938- 2946, doi: 10.1109/ICCV.2015.336. [4] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735. [5] F. Walch, C. Hazirbas, L. Leal-Taixe, T. Sattler, S. Hilsenbeck, and D. Cremers, “Image-based localization using lstms for structured feature correlation,” 2017 IEEE International Conference on Computer Vision (ICCV), 2017. [6] A. Kendall and R. Cipolla, ”Geometric Loss Functions for Camera Pose Regression with Deep Learning,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6555-6564, doi: 10.1109/CVPR.2017.694. [7] C. Szegedy et al., ”Going deeper with convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1-9, doi: 10.1109/CVPR.2015.7298594. [8] A. Chaudhary, R. Mishra, B. Kalyan, and M. Chitre, ”Development of an Underwater Simulator using Unity3D and Robot Operating Systems”, 2021 OCEANS - San Diego, in press. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Authors: Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction I Introduction II Method II Method III Datasets III Datasets IV Experiments, Acknowledgment, and References IV Experiments, Acknowledgment, and References IV. EXPERIMENTS We test three model configurations on both the simulator and tank datasets. First, we implement a pose regression model based on GoogLeNet [7] as our baseline model. Secondly, we implement a model using ResNet-50 [9] to evaluate the improvement possible by use of a deeper network. ResNet allows us to have deeper networks with more free parameters, and tries to avoid the problem of overfitting by having residual connections between layers [9]. Thirdly, we implement a pose regression model using an LSTM as an intermediate layer. The results indicate that all three configurations can perform well in both simulated and tank datasets as shown in Table I. The errors are minimal and of comparable magnitude to the noise in the pose recorded by the camera sensors. Fig. 4 shows that the trajectories predicted by the models are very close to the actual trajectories in terms of both position and orientation. With the simulator dataset, which is free of noise, turbidity, light distortion, and other challenges that may be observed in real underwater settings, the ResNet-50 and LSTM-based model performed better than the baseline model. On the other hand, with the tank datasets with some distortions typical of underwater scenarios, ResNet-50 performed worse than the baseline model, whereas the LSTM model did better than baseline with dataset #1 (which mostly featured translation but almost no rotation). This suggests the ResNet-50 architecture may be slightly overfitting despite the regularization, so it is not able to provide better performance in the tank dataset. We also note that data augmentation significantly improves the model performance, so in cases where there is no significant rotation, the use of data from both cameras can be used to bolster performance. Overall, these methods are robust for application in real underwater environments, and show promise for use in open water settings, where they will be tested next. ACKNOWLEDGMENT This research project is supported by A*STAR under its RIE2020 Advanced Manufacturing and Engineering (AME) Industry Alignment Fund - Pre-Positioning (IAF-PP) Grant No. A20H8a0241. REFERENCES [1] J. Gonzalez-Garcıa, A. Gomez-Espinosa, E. Cuan-Urquizo, L. G. ´ Garcıa-Valdovinos, T. Salgado-Jimenez, and J. A. E. Cabello, “Au-tonomous Underwater Vehicles: Localization, Navigation, and Commu- nication for Collaborative Missions,” Applied Sciences, vol. 10, no. 4, p. 1256, Feb. 2020. [2] L. Peng and M. Chitre, ”Regressing Poses from Monocular Images in an Underwater Environment”, 2022 OCEANS - Chennai, in press. [3] A. Kendall, M. Grimes and R. Cipolla, ”PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization,” 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 2938- 2946, doi: 10.1109/ICCV.2015.336. [4] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735. [5] F. Walch, C. Hazirbas, L. Leal-Taixe, T. Sattler, S. Hilsenbeck, and D. Cremers, “Image-based localization using lstms for structured feature correlation,” 2017 IEEE International Conference on Computer Vision (ICCV), 2017. [6] A. Kendall and R. Cipolla, ”Geometric Loss Functions for Camera Pose Regression with Deep Learning,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6555-6564, doi: 10.1109/CVPR.2017.694. [7] C. Szegedy et al., ”Going deeper with convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1-9, doi: 10.1109/CVPR.2015.7298594. [8] A. Chaudhary, R. Mishra, B. Kalyan, and M. Chitre, ”Development of an Underwater Simulator using Unity3D and Robot Operating Systems”, 2021 OCEANS - San Diego, in press. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Underwater Visual Localization Using Machine Learning and LSTM: Experiments, and References

Authors:
(1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore;
(2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore;
(3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore;
(4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore;
(5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore;
(6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction II Method III Datasets IV Experiments, Acknowledgment, and References III. DATASETS To train and test our model, we used one dataset collected from an underwater robotics simulator [8] as shown in Fig. 3 as well as two datasets collected from a tank as shown in Fig. 2. In the simulator dataset, we operated the ROV in simulation to perform inspection on a vertical pipe in a spiral motion. The total spatial extent covered by the ROV during the inspection is about 2×4×2 m. 14,400 samples of image-pose pair data were collected. In the first tank dataset, we operated the ROV in a lawnmower path with translations only (Fig.2), and the rotations were minimal. We collected 3,437 data samples. In the second tank dataset, the ROV primarily performed rotation maneuvers at 5 selected points. We collected 4,977 data samples. We augmented the left-camera dataset by adding the right-camera data, and thereby using the geometry of the stereo camera placement to provide more training data. This worked well and yielded better performance. The total spatial extent covered in tank datasets was 0.4×0.6×0.2 m. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Authors: Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction I Introduction II Method II Method III Datasets III Datasets IV Experiments, Acknowledgment, and References IV Experiments, Acknowledgment, and References III. DATASETS To train and test our model, we used one dataset collected from an underwater robotics simulator [8] as shown in Fig. 3 as well as two datasets collected from a tank as shown in Fig. 2. In the simulator dataset, we operated the ROV in simulation to perform inspection on a vertical pipe in a spiral motion. The total spatial extent covered by the ROV during the inspection is about 2×4×2 m. 14,400 samples of image-pose pair data were collected. In the first tank dataset, we operated the ROV in a lawnmower path with translations only (Fig.2), and the rotations were minimal. We collected 3,437 data samples. In the second tank dataset, the ROV primarily performed rotation maneuvers at 5 selected points. We collected 4,977 data samples. We augmented the left-camera dataset by adding the right-camera data, and thereby using the geometry of the stereo camera placement to provide more training data. This worked well and yielded better performance. The total spatial extent covered in tank datasets was 0.4×0.6×0.2 m. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Underwater Visual Localization Using Machine Learning and LSTM: Datasets

Authors:
(1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore;
(2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore;
(3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore;
(4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore;
(5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore;
(6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction II Method III Datasets IV Experiments, Acknowledgment, and References II. METHOD We implement two different architectures. The first uses pretrained deep convolutional neural networks (DCNN) to extract features from the input images. The resulting feature map is then passed to an affine regressor consisting of dense neural layers to output a 7-dimensional pose vector estimates. The second architecture adds an additional LSTM layer between the DCNN and affine regressor to perform dimensionality reduction by assessing the spatial structure of the image. This is done by four LSTMs which parse the DCNN-output feature map in different directions starting at each of the four image corners to process the spatial trends, and compress it into lower-dimensional information which is easier processed by the affine regressor. The input images used in the training are rescaled to 256×256 pixels before cropping into a 224×224 feature input using centre cropping. To speed up training, the images are normalized by the mean and standard deviation of the images. The poses are also normalized to lie within [-1, 1]. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Authors: Authors: (1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore; (2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore; (3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore; (4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore; (5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore; (6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore. Table of Links I Introduction I Introduction II Method II Method III Datasets III Datasets IV Experiments, Acknowledgment, and References IV Experiments, Acknowledgment, and References II. METHOD We implement two different architectures. The first uses pretrained deep convolutional neural networks (DCNN) to extract features from the input images. The resulting feature map is then passed to an affine regressor consisting of dense neural layers to output a 7-dimensional pose vector estimates. The second architecture adds an additional LSTM layer between the DCNN and affine regressor to perform dimensionality reduction by assessing the spatial structure of the image. This is done by four LSTMs which parse the DCNN-output feature map in different directions starting at each of the four image corners to process the spatial trends, and compress it into lower-dimensional information which is easier processed by the affine regressor. The input images used in the training are rescaled to 256×256 pixels before cropping into a 224×224 feature input using centre cropping. To speed up training, the images are normalized by the mean and standard deviation of the images. The poses are also normalized to lie within [-1, 1]. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Stories, News & Mentions about BHARATX

Bharatx’s Stories on HackerNoon

Bharatx's News & Mentions