Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues

Abstract

Abstract-In this paper, the problem of multi-target tracking with single camera in complex scenes is addressed. A new approach is proposed for multi-target tracking problem that learns from hierarchy of convolution features. First fast Region-based Convolutional Neutral Networks is trained to detect pedestrian in each frame. Then cooperate it with correlation filter tracker which learns target's appearance from pretrained convolutional neural networks. Correlation filter learns from middle and last convolutional layers to enhances targets localization. However correlation filters fail in case of targets full occlusion. This lead to separated tracklets (mini-trajectories) problem. So a post processing step is added to link separated tracklets with minimum-cost network flow. A cost function is used, that depends on motion cues in associating short tracklets. Experimental results on MOT2015 benchmark show that the proposed approach produce comparable result against state-of-the-art approaches. It shows an increase 4.5 % in multiple object tracking accuracy. Also mostly tracked targets is 12.9% vs 7.5% against state-ofthe-art minimum-cost network flow tracker.

Recurrent Metric Networks and Batch Multiple Hypothesis for Multi-Object Tracking

“…With the great success of deep convolutional neural networks (CNN) in the computer vision community, some multi-object tracking methods have applied CNN based features [22], [51] or Siamese CNN based similarity metric [20], [21]. In addition, some works utilize recurrent neural networks (RNN) for multi-object tracking.…”

“…Recently, deep learning has achieved great success in many vision tasks such as image classification [15], object detection [16], image segmentation [17], and parsing [18]. Some attempts of convolutional neural networks (CNN) have been made into single object tracking [19] and multi-object tracking [20]- [22]. These methods either apply CNN as a powerful feature extractor [22] or further use CNN as a siamese network for similarity metric learning [20], [21].…”

“…Some attempts of convolutional neural networks (CNN) have been made into single object tracking [19] and multi-object tracking [20]- [22]. These methods either apply CNN as a powerful feature extractor [22] or further use CNN as a siamese network for similarity metric learning [20], [21]. These methods mainly consider the previous nearest frames to update the extractor or the siamese network, which is not robust for error or missing detections.…”