Integrated Object Detection and Tracking with Tracklet-Conditioned Detection

Abstract

Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the tracking. To increase synergy, we propose to more tightly integrate the tasks by conditioning the object detection in the current frame on tracklets computed in prior frames. With this approach, the object detection results not only have high detection responses, but also improved coherence with the existing tracklets. This greater coherence leads to estimated object trajectories that are smoother and more stable than the jittered paths obtained without tracklet-conditioned detection. Over extensive experiments, this approach is shown to achieve state-of-the-art performance in terms of both detection and tracking accuracy, as well as noticeable improvements in tracking stability.

References in corpus (13)

• Deep Residual Learning for Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Deformable Convolutional Networks
• Flow-Guided Feature Aggregation for Video Object Detection
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
• Dual Path Networks
• Crafting GBD-Net for Object Detection
• On The Stability of Video Detection and Tracking
• Recurrent Autoregressive Networks for Online Multi-Object Tracking
• Towards High Performance Video Object Detection

Cited by in corpus (9)

• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• Tracklets Predicting Based Adaptive Graph Tracking
• Tracking Objects as Points
• Track to Detect and Segment: An Online Multi-Object Tracker
• TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
• ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
• CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
• Plug & Play Convolutional Regression Tracker for Video Object Detection
• Feature Flow: In-network Feature Flow Estimation for Video Object Detection