Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues

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.

Authors and Affiliations

Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif, Ibrahim Farag

Keywords

Related Articles

Simplex Parallelization in a Fully Hybrid Hardware Platform

The simplex method has been successfully used in solving linear programming (LP) problems for many years. Parallel approaches have also extensively been studied due to the intensive computations required, especially for...

Testing the Use of the Integrated Model in Designing the Management Information Systems by Using the Mathematical Probability Theories

The integrated model is a new model that is recently developed to decrease from the classical approach weaknesses and problems in building the management information systems (MIS’s) that are used to solve the management...

Skill Evaluation for Newly Graduated Students Via Online Test

Every year in each university many students are graduated holding a first university degree. For example Bachelor degree in Computer Science. Most of those students have a motivation to continue with further studies to g...

A Review on Event-Based Epidemic Surveillance Systems that Support the Arabic Language

With the revolution of the internet, many event-based systems have been developed for monitoring epidemic threats. These systems rely on unstructured data gathered from various online sources. Moreover, some systems are...

Integrated Routing Protocol for Opportunistic Networks

In opportunistic networks the existence of a simultaneous path is not assumed to transmit a message between a sender and a receiver. Information about the context in which the users communicate is a key piece of knowledg...

Download PDF file
  • EP ID EP240719
  • DOI 10.14569/IJACSA.2017.081129
  • Views 105
  • Downloads 0

How To Cite

Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif, Ibrahim Farag (2017). Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues. International Journal of Advanced Computer Science & Applications, 8(11), 217-222. https://europub.co.uk/articles/-A-240719