�ݺ�ߣshows by User: UtkarshContractor

�ݺ�ߣshows by User: UtkarshContractor / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: UtkarshContractor / Wed, 24 Jan 2018 15:56:23 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: UtkarshContractor Surveillance scene classification using machine learning /slideshow/surveillance-scene-classification-using-machine-learning-86641328/86641328 surveillancesceneclassificationusingmachinelearning-180124155623
The problem of scene classification in surveillance footage is of great importance for ensuring security in public areas. With challenges such as low quality feeds, occlusion, viewpoint variations, background clutter etc. The task is both challenging and error-prone. Therefore it is important to keep the false positives low to maintain a high accuracy of detection. In this paper, we adapt high performing CNN architectures to identify abandoned luggage in a surveillance feed. We explore several CNN based approaches, from Transfer Learning on the Imagenet dataset to object classification using Faster R-CNNs on the COCO dataset. Using network visualization techniques, we gain insight into what the neural network sees and the basis of classification decision. The experiments have been conducted on real world datasets, and highlights the complexity in such classifications. Obtained results indicate that a combination of proposed techniques outperforms the individual approaches.]]>
The problem of scene classification in surveillance footage is of great importance for ensuring security in public areas. With challenges such as low quality feeds, occlusion, viewpoint variations, background clutter etc. The task is both challenging and error-prone. Therefore it is important to keep the false positives low to maintain a high accuracy of detection. In this paper, we adapt high performing CNN architectures to identify abandoned luggage in a surveillance feed. We explore several CNN based approaches, from Transfer Learning on the Imagenet dataset to object classification using Faster R-CNNs on the COCO dataset. Using network visualization techniques, we gain insight into what the neural network sees and the basis of classification decision. The experiments have been conducted on real world datasets, and highlights the complexity in such classifications. Obtained results indicate that a combination of proposed techniques outperforms the individual approaches.]]> Wed, 24 Jan 2018 15:56:23 GMT /slideshow/surveillance-scene-classification-using-machine-learning-86641328/86641328 UtkarshContractor@slideshare.net(UtkarshContractor) Surveillance scene classification using machine learning UtkarshContractor The problem of scene classification in surveillance footage is of great importance for ensuring security in public areas. With challenges such as low quality feeds, occlusion, viewpoint variations, background clutter etc. The task is both challenging and error-prone. Therefore it is important to keep the false positives low to maintain a high accuracy of detection. In this paper, we adapt high performing CNN architectures to identify abandoned luggage in a surveillance feed. We explore several CNN based approaches, from Transfer Learning on the Imagenet dataset to object classification using Faster R-CNNs on the COCO dataset. Using network visualization techniques, we gain insight into what the neural network sees and the basis of classification decision. The experiments have been conducted on real world datasets, and highlights the complexity in such classifications. Obtained results indicate that a combination of proposed techniques outperforms the individual approaches. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/surveillancesceneclassificationusingmachinelearning-180124155623-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> The problem of scene classification in surveillance footage is of great importance for ensuring security in public areas. With challenges such as low quality feeds, occlusion, viewpoint variations, background clutter etc. The task is both challenging and error-prone. Therefore it is important to keep the false positives low to maintain a high accuracy of detection. In this paper, we adapt high performing CNN architectures to identify abandoned luggage in a surveillance feed. We explore several CNN based approaches, from Transfer Learning on the Imagenet dataset to object classification using Faster R-CNNs on the COCO dataset. Using network visualization techniques, we gain insight into what the neural network sees and the basis of classification decision. The experiments have been conducted on real world datasets, and highlights the complexity in such classifications. Obtained results indicate that a combination of proposed techniques outperforms the individual approaches.

Surveillance scene classification using machine learning from Utkarsh Contractor

]]> 243 1 https://cdn.slidesharecdn.com/ss_thumbnails/surveillancesceneclassificationusingmachinelearning-180124155623-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-UtkarshContractor-48x48.jpg?cb=1542014492 Design and development of onsite search application from bottom up. Experience working with Lucene / Solr and Google Search Appliance. Designed and developed analytics tools for web traffic analysis, marketing, e-commerce and consumer insights teams. Extensive experience working with Analytics and Optimization platforms along with other web master tools to track various metrics. Responsible to understand and assist the requestor in refining business requirement documentation as well as creating technical and functional specifications for software applications. Developing Unix and Java based tools for automation testing, to help QA team with testing new and exiting system features....