-
公开(公告)号：US20230047937A1
公开(公告)日：2023-02-16
申请号：US17552868
申请日：2021-12-16
发明人： Jayavardhana Rama GUBBI LAKSHMINARASIMHA , Vartika Sengar , Vivek Bangalore Sampathkumar , Aparna Kanakatte Gurumurthy , Murali Poduval , Balamuralidhar Purushothaman , Karthik Seemakurthy , Avik Ghose , Srinivasan Jayaraman
摘要： The disclosure herein relates to methods and systems for generating an end-to-end de-smoking model for removing smoke present in a video. Conventional data-driven based de-smoking approaches are limited mainly due to lack of suitable training data. Further, the conventional data-driven based de-smoking approaches are not end-to-end for removing the smoke present in the video. The de-smoking model of the present disclosure is trained end-to-end with the use of synthesized smoky video frames that are obtained by source aware smoke synthesis approach. The end-to-end de-smoking model localize and remove the smoke present in the video, using dynamic properties of the smoke. Hence the end-to-end de-smoking model simultaneously identifies the regions affected with the smoke and performs the de-smoking with minimal artifacts. localized smoke removal and color restoration of a real-time video.
-
公开(公告)号：US20230016233A1
公开(公告)日：2023-01-19
申请号：US17476512
申请日：2021-09-16
摘要： Automation is the key to build efficient workflows with minimum effort consumption. However, there is a large gap in workflow synthesis for automated AI application development. Computer vision workflow synthesis largely rely on domain expert due to lack of generalization over solution search space for given goal. This search space for creating suitable solution(s) using available algorithms is quite vast, which makes exploratory work of solution building a time-, effort- and intellect intensive endeavor. Embodiments of the present disclosure provide system and method for goal-driven algorithm selection approach for building computer vision workflows on the fly. The system generates one or more task workflows with associated success probability depending on initial conditions and input natural language goal query by combining various image processing algorithms. Symbolic AI planning is aided by Reinforcement Learning to recommend optimal workflows that are robust and adaptive to changes in the environment.
-
公开(公告)号：US12100124B2
公开(公告)日：2024-09-24
申请号：US17552868
申请日：2021-12-16
发明人： Jayavardhana Rama Gubbi Lakshminarasimha , Vartika Sengar , Vivek Bangalore Sampathkumar , Aparna Kanakatte Gurumurthy , Murali Poduval , Balamuralidhar Purushothaman , Karthik Seemakurthy , Avik Ghose , Srinivasan Jayaraman
CPC分类号： G06T5/70 , G06T5/50 , G06T7/269 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084
摘要： The disclosure herein relates to methods and systems for generating an end-to-end de-smoking model for removing smoke present in a video. Conventional data-driven based de-smoking approaches are limited mainly due to lack of suitable training data. Further, the conventional data-driven based de-smoking approaches are not end-to-end for removing the smoke present in the video. The de-smoking model of the present disclosure is trained end-to-end with the use of synthesized smoky video frames that are obtained by source aware smoke synthesis approach. The end-to-end de-smoking model localize and remove the smoke present in the video, using dynamic properties of the smoke. Hence the end-to-end de-smoking model simultaneously identifies the regions affected with the smoke and performs the de-smoking with minimal artifacts. localized smoke removal and color restoration of a real-time video.
-
公开(公告)号：US12094035B2
公开(公告)日：2024-09-17
申请号：US17645116
申请日：2021-12-20
发明人： Jayavardhana Rama Gubbi Lakshminarasimha , Karthik Seemakurthy , Vartika Sengar , Aparna Kanakatte Gurumurthy , Avik Ghose , Balamuralidhar Purushothaman , Murali Poduval , Jayeeta Saha , Srinivasan Jayaraman , Vivek Bangalore Sampathkumar
CPC分类号： G06T11/001 , G06T7/90 , G06V10/56 , G06T2207/10016
摘要： The disclosure herein relates to methods and systems for localized smoke removal and color restoration of a real-time video. Conventional techniques apply the de-smoking process only on a single image, by finding the regions having the smoke, based on manual air-light estimation. In addition, regaining original colors of de-smoked image is quite challenging. The present disclosure herein solves the technical problems. In the first stage, video frames having the smoky and smoke-free video frames are identified, from the video received in the real-time. In the second stage, an air-light is estimated automatically using a combined feature map. An intermediate de-smoked video frame for each smoky video frame is generated based on the air-light using a de-smoking algorithm. In the third and the last stage, a smoke-free video reference frame is used to compensate for color distortions introduced by the de-smoking algorithm in the second stage.
-
5.发明公开公开(公告)号：US20230376781A1
公开(公告)日：2023-11-23
申请号：US18199708
申请日：2023-05-19
发明人： Abhishek Roy Choudhury , Vighnesh Vatsal , Mehesh Rangarajan , Naveen Kumar Basa Anitha , Aditya Kapoor , Jayavardhana Rama Gubbi Lakshminarasimha , Aravindhan Saravanan , Vartika Sengar , Balamuralidhar Purushothaman , Arpan Pal , Nijil George
IPC分类号： G06N3/092
CPC分类号： G06N3/092
摘要： This disclosure relates generally to systems and methods for autonomous task composition of vision pipelines using an algorithm selection framework. The framework leverages transformer architecture along with deep reinforcement learning techniques to search an algorithmic space for unseen solution templates. In an embodiment, the present disclosure describes a two stage process of identifying the vision pipeline for a particular task. At first stage, a high-level sequence of the vision pipeline is provided by a symbolic planner to create the vision workflow. At second stage, suitable algorithms for each high-level task are selected. This is achieved by performing a graph search using a transformer architecture over an algorithmic space on each component of generated workflow. In order to make the system more robust, weights of embedding, key and query networks of a visual transformer are updated with a Deep Reinforcement Learning framework that uses Proximal Policy Optimization (PPO) as underlying algorithm.
-
-
-
-
搜索结果
5 条记录 (耗时 0.016 秒)
