知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.014 seconds)

    ADAPTIVE PERCEPTUAL QUALITY BASED CAMERA TUNING USING REINFORCEMENT LEARNING
    1.
    发明公开
    ADAPTIVE PERCEPTUAL QUALITY BASED CAMERA TUNING USING REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20240089592A1

    公开(公告)日：2024-03-14

    申请号：US18466296

    申请日：2023-09-13

    Applicant: NEC Laboratories America, Inc.

    Inventor： Kunal Rao ,  Sibendu Paul ,  Giuseppe Coviello ,  Murugan Sankaradas ,  Oliver Po ,  Srimat Chakradhar

    IPC: H04N23/60 ,  H04N23/61

    CPC classification number: H04N23/64 ,  H04N23/61

    Abstract: Systems and methods are provided for dynamically tuning camera parameters in a video analytics system to optimize analytics accuracy. A camera captures a current scene, and optimal camera parameter settings are learned and identified for the current scene using a Reinforcement Learning (RL) engine. The learning includes defining a state within the RL engine as a tuple of two vectors: a first representing current camera parameter values and a second representing measured values of frames of the current scene. Quality of frames is estimated using a quality estimator, and camera parameters are adjusted based on the quality estimator and the RL engine for optimization. Effectiveness of tuning is determined using perceptual Image Quality Assessment (IQA) to quantify a quality measure. Camera parameters are adaptively tuned in real-time based on learned optimal camera parameter settings, state, quality measure, and set of actions, to optimize the analytics accuracy for video analytics tasks.

    VIDEO ANALYTICS ACCURACY USING TRANSFER LEARNING
    4.
    发明公开
    VIDEO ANALYTICS ACCURACY USING TRANSFER LEARNING 审中-公开

    公开(公告)号：US20240037778A1

    公开(公告)日：2024-02-01

    申请号：US18361340

    申请日：2023-07-28

    Applicant: NEC Laboratories America, Inc.

    Inventor： Kunal Rao ,  Giuseppe Coviello ,  Murugan Sankaradas ,  Oliver Po ,  Srimat Chakradhar ,  Sibendu Paul

    IPC: G06T7/70 ,  G06T7/00 ,  G06V10/25 ,  G06V40/10

    CPC classification number: G06T7/70 ,  G06T7/0002 ,  G06V10/25 ,  G06V40/103 ,  G06V2201/07 ,  G06T2207/30242

    Abstract: Systems and methods are provided for increasing accuracy of video analytics tasks in real-time by acquiring a video using video cameras, and identifying fluctuations in the accuracy of video analytics applications across consecutive frames of the video. The identified fluctuations are quantified based on an average relative difference of true-positive detection counts across consecutive frames. Fluctuations in accuracy are reduced by applying transfer learning to a deep learning model initially trained using images, and retraining the deep learning model using video frames. A quality of object detections is determined based on an amount of track-ids assigned by a tracker across different video frames. Optimization of the reduction of fluctuations includes iteratively repeating the identifying, the quantifying, the reducing, and the determining the quality of object detections until a threshold is reached. Model predictions for each frame in the video are generated using the retrained deep learning model.

    REINFORCEMENT-LEARNING BASED SYSTEM FOR CAMERA PARAMETER TUNING TO IMPROVE ANALYTICS
    5.
    发明申请
    REINFORCEMENT-LEARNING BASED SYSTEM FOR CAMERA PARAMETER TUNING TO IMPROVE ANALYTICS 有权

    公开(公告)号：US20220414935A1

    公开(公告)日：2022-12-29

    申请号：US17825519

    申请日：2022-05-26

    Applicant: NEC Laboratories America, Inc.

    Inventor： Kunal Rao ,  Giuseppe Coviello ,  Murugan Sankaradas ,  Oliver Po ,  Srimat Chakradhar ,  Sibendu Paul

    IPC: G06T7/80 ,  G06T7/00

    Abstract: A method for automatically adjusting camera parameters to improve video analytics accuracy during continuously changing environmental conditions is presented. The method includes capturing a video stream from a plurality of cameras, performing video analytics tasks on the video stream, the video analytics tasks defined as analytics units (AUs), applying image processing to the video stream to obtain processed frames, filtering the processed frames through a filter to discard low-quality frames and dynamically fine-tuning parameters of the plurality of cameras. The fine-tuning includes passing the filtered frames to an AU-specific proxy quality evaluator, employing State-Action-Reward-State-Action (SARSA) reinforcement learning (RL) computations to automatically fine-tune the parameters of the plurality of cameras, and based on the reinforcement computations, applying a new policy for an agent to take actions and learn to maximize a reward.

Patent Agency Ranking