Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking
Multi-object tracking (MOT) has made great progress in recent years, but there are still some problems. Most MOT algorithms follow tracking-by-detection framework, which separates detection and tracking into two independent parts. Early tracking-by-detection algorithms need to do two feature extractions for detection and tracking. Recently, some algorithms make the feature extraction into one network, but the tracking part still relies on data association and needs complex post-processing for life cycle management. Those methods do not combine detection and tracking well. In this paper, we present a novel network to realize joint multi-object detection and tracking in an end-to-end way, called Global Correlation Network (GCNet). Different from most object detection methods, GCNet introduces the global correlation layer for regression of absolute size and coordinates of bounding boxes instead of offsets prediction. The pipeline of detection and tracking by GCNet is conceptually simple, which does not need non-maximum suppression, data association, and other complicated tracking strategies. GCNet was evaluated on a multi-vehicle tracking dataset, UA-DETRAC, and demonstrates promising performance compared to the state-of-the-art detectors and trackers.
Code (0)
등록된 구현이 없습니다.
Tasks
ManagementMulti-Object TrackingObjectobject-detectionObject DetectionObject TrackingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence
Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios. Most existing joint models rely entirely …
Graph Neural NetworkIntent DetectionSemantic Frame Parsingslot-filling+1Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving
Multi-object tracking (MOT) with camera-LiDAR fusion demands accurate results of object detection, affinity computation and data association in real time. This paper presents an efficient multi-modal MOT framework with o…
Autonomous DrivingMulti-Object TrackingObjectobject-detection+2Joint Counting, Detection and Re-Identification for Multi-Object Tracking
The recent trend in 2D multiple object tracking (MOT) is jointly solving detection and tracking, where object detection and appearance feature (or motion) are learned simultaneously. Despite competitive performance, in c…
Multi-Object TrackingMultiple Object TrackingObjectobject-detection+2Structural Kernel Learning for Large Scale Multiclass Object Co-Detection
Exploiting contextual relationships across images has recently proven key to improve object detection. The resulting object co-detection algorithms, however, fail to exploit the correlations between multiple classes and,…
Objectobject-detectionObject DetectionShift, Scale and Rotation Invariant Multiple Object Detection using Balanced Joint Transform Correlator
The Polar Mellin Transform (PMT) is a well-known technique that converts images into shift, scale and rotation invariant signatures for object detection using opto-electronic correlators. However, this technique cannot b…
object-detectionObject Detection