Integration Between Cascade Region-Based Convolutional Neural Network and Bi-Directional Feature Pyramid Network for Live Object Tracking and Detection.
Lehai ZhongJiao LiFeifan ZhouXiaoan BaoWeiyin XingZhengyong HanJinsheng LuoPublished in: Traitement du Signal (2021)
Keyphrases
- object tracking
- bi directional
- convolutional neural network
- video surveillance systems
- histograms of oriented gradients
- mean shift
- particle filter
- partial occlusion
- scene segmentation
- crowded scenes
- human detection
- video sequences
- image sequences
- appearance model
- video surveillance
- face detection
- computer vision
- multiple object tracking
- moving objects
- sparse representation
- object detection
- appearance modeling
- data association
- visual tracking
- detection method
- particle filtering
- multi camera
- detection rate
- associative memory
- detection algorithm
- object appearance
- robust object tracking
- multiscale
- feature vectors
- image segmentation
- high dimensional
- image features
- multi class
- object location
- nearest neighbor
- tracking objects
- pedestrian detection