Person re-ID while Crossing Different Cameras: Combination of Salient-Gaussian Weighted BossaNova and Fisher Vector Encodings
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 9
Abstract
Person re-identification (re-ID) is a challenging task in the camera surveillance field, since it addresses the problem of re-identifying people across multiple non-overlapping cameras. Most of existing approaches have been concentrated on: 1) achieving a robust and effective feature representation; and 2) enforcing discriminative metric learning to predict if two images represent the same identity. In this context, we present a new approach for person re-ID built upon multi-level descriptors. This is achieved by combining three complementary representations: salient-Gaussian Fisher Vector (SGFV) encoding method, salient-Gaussian BossaNova (SGBN) histogram encoding method and deep Convolutional Neural Network (CNN) features. The two first methods adapt the histogram encoding framework to the person re-ID task. This is achieved by integrating the pedestrian saliency map and the spatial location information, in the histogram encoding process. On one hand, human saliency is reliable and distinctive in the person re-ID task, since it can model the uniqueness of the identity. On the other hand, localizing a person in the image can effectively discard noisy background information. Finally, one of the most advanced metric learning in person re-ID: the Cross-view Quadratic Discriminant Analysis (XQDA) is applied on the top of the resulting description. The proposed method yields promising person re-ID results on two challenging image-based person re-ID benchmarks: CUHK03 and Market-1501.
Authors and Affiliations
Mahmoud Mejdoub, Salma Ksibi, Chokri Ben Amar, Mohamed Koubaa
Multi-Domain Modeling and Simulation of an Aircraft System for Advanced Vehicle-Level Reasoning Research and Development
In this paper, we describe a simulation based health monitoring system test-bed for aircraft systems. The purpose of the test-bed is to provide a technology neutral basis for implementing and evaluation of reasoning syst...
Frequency Domain Analysis for Assessing Fluid Responsiveness by Using Instantaneous Pulse Rate Variability
In the ICU, fluid therapy is conventional strategy for the patient in shock. However, only half of ICU patients have well-responses to fluid therapy, and fluid loading in non-responsive patient delays definitive therapy....
Convolutional Neural Network Architecture for Plant Seedling Classification
Weed control is a challenging problem that may face crops productivity. Weeds are perceived as an important problem because they conduce to reduce crop yields due to the expanding competition for nutrients, water, and su...
Implementation of Locally Weighted Projection Regression Network for Concurrency Control In Computer Aided Design
This paper presents implementation of locally weighted projection regression (LWPR) network method for concurrency control while developing dial of a fork using Autodesk inventor 2008. The LWPR learns the objects and the...
A New Project Risk Management Model based on Scrum Framework and Prince2 Methodology
With increasing competition in the software industry, software companies need to effectively manage the risks of software projects with minimal time and cost to deliver high quality products. High frequencies of warning...