Abstract
Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, fine-grained data (attributes), the Local Features are not employed at semantic level in online stage of Re-ID task, furthermore, the imbalanced data problem of attributes are not taken into consideration. This paper has proposed a Unified Re-ID system consisted of three main modules such as Pedestrian Attribute Ontology (PAO), Local Multi-task DCNN (Local MDCNN), Imbalance Data Solver (IDS). The new main point of our Re-ID system is the power of mutual support of PAO, Local MDCNN and IDS to exploit the inner-group correlations of attributes and pre-filter the mismatch candidates from Gallery set based on semantic information as Fashion Attributes and Facial Attributes, to solve the imbalanced data of attributes without adjusting network architecture and data augmentation. We experimented on the well-known Market1501 dataset. The experimental results have shown the effectiveness of our Re-ID system and it could achieve the higher performance on Market1501 dataset in comparison to some state-of-the-art Re-ID methods.
Highlights
Re-ID is the problem of recognising and associating a person at different physical locations over time after the person had been previously observed visually elsewhere
The main contributions of this paper are as follows: 1) We propose the Pedestrian Attribute Ontology to conduct Pedestrian Attribute Learning Process and Re-ID process; 2) We propose the Pedestrian Attribute Learning Model based on Local Multi-task learning; 3) We propose integrating Imbalanced Data Solver based on Matthews correlation coefficient (MCC) to Re-ID system; 4) We propose new Re-ID method based on Deep Global Features and Pedestrian Semantic Information
Instead of distributing each attribute over multiple parts and concatenating local and global deep features, we proposed novel methods for improvement: 1) We build a Pedestrian Attribute Ontology (PAO) for better attributes learning, and for expanding in the future; 2) Based on PAO, we build a Local Multi-task Deep Convolution Neuron Network (DCNN) model (Local Multi-task Deep Convolution Neuron Network (MDCNN)) to exploit inner group and inter group correlations between attributes; 3) We incorporate an Imbalanced Data Solver (IDS) to our Pedestrian Attribute Recognition module; and 4) we build a novel Person Re-identification system flexibly combining global deep www.ijacsa.thesai.org features and pedestrian semantic information
Summary
Re-ID is the problem of recognising and associating a person at different physical locations over time after the person had been previously observed visually elsewhere. To obtain more discriminative features to deal with the inter-class challenge, some works try to extract local features from local regions in different ways, such as pose normalization [13,14,15], part-based learning [16,17,18,19], or attention mechanism [20,21,22,23] These great works gain very high performance in accuracy and mAP, they are still only employed deep features, which do not contain semantic information and cannot be explained by human. The main contributions of this paper are as follows: 1) We propose the Pedestrian Attribute Ontology to conduct Pedestrian Attribute Learning Process and Re-ID process; 2) We propose the Pedestrian Attribute Learning Model based on Local Multi-task learning; 3) We propose integrating Imbalanced Data Solver based on MCC to Re-ID system; 4) We propose new Re-ID method based on Deep Global Features and Pedestrian Semantic Information
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
