Multi-domain Cross-dataset and Camera Style Transfer for Person Re-Identification
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.8, No. 5)Publication Date: 2019-10-15
Authors : Rabia Tahir Keyang Cheng Lubamba Kasangu Eric; Muhammad Saddam Khokhar;
Page : 2034-2041
Keywords : Person re-identification; Camera Style Transfer; GAN; Xception;
Abstract
The major reason of performance drop in person reidentification (re-id) models is domain gap between various datasets. Each person re-id dataset is different from other dataset because of change in lightning conditions, camera angle, pose, illumination, background and resolution. This results in domain gap between these datasets and leads to performance drop in person re-identification models. The domain gap not only exits between distinct datasets but it is also present in a dataset which contains images taken from multiple cameras. Generative Adversarial Networks (GANs) have achieved successful results in various fields, especially for image-to-image translation. In this paper, we propose an unsupervised domain adaptation method based on ComboGAN and Xception to perform cross-dataset and camera style translation. Our framework generates images in different styles of a single person according to various domains. Experimental results show the effectiveness of the proposed model on two popular re-id datasets Market-1501 and PETA.
Other Latest Articles
- Training and Development of Professional Skills: An Analysis of activity in Professional Skills
- An Assessment of the Visual Features Extractions for the Audio-Visual Speech Recognition
- Effective Zone Based Routing Protocols for MANET
- Fuzzy Logic based Channel Selection Algorithm for Wireless Mesh Networks
- Cooperative Dual Relay Overlay CR NOMA Network with Outdated CSI
Last modified: 2019-11-11 17:54:43