×

Real-time object analysis with occlusion handling

  • US 9,582,895 B2
  • Filed: 05/22/2015
  • Issued: 02/28/2017
  • Est. Priority Date: 05/22/2015
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method, comprising the steps of:

  • receiving a video sequence comprising detection results from one or more detectors, the detection results identifying one or more objects;

    applying a clustering process to the detection results to identify one or more clusters associated with the one or more objects, wherein the clustering process is applied to the video sequence on a frame-by-frame basis, and wherein applying the clustering process comprises;

    detecting one or more non-associated detections, wherein the one or more non-associated detections have not been assigned to an existing cluster;

    applying a non-maximum suppression process to the one or more non-associated detections to generate one or more results;

    evaluating the one or more results with a confidence score for the one or more non-associated detections, wherein the confidence score comprises a depth-height map and a detection frequency; and

    instantiating a new cluster or eliminating one or more existing clusters based on the confidence score;

    determining spatial and temporal information for each of the one or more clusters;

    associating the one or more clusters to the detection results based on the spatial and temporal information in consecutive frames of the video sequence to generate tracking information;

    generating one or more target tracks based on the tracking information for the one or more clusters; and

    consolidating the one or more target tracks to generate refined tracks for the one or more objects;

    wherein the steps are performed by at least one processor device coupled to a memory.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×