22 December 2020 in IEEE Access
Existing night vehicle detection methods mainly detect vehicles by detecting headlights or taillights. However, these features are adversely affected by the complex road lighting environment. In this paper, a cascade detection network framework FteGanOd is proposed with a feature translate-enhancement (FTE) module and the object detection (OD) module. First, the FTE module is built based on CycleGAN and multi-scale feature fusion is proposed to enhance the detection of vehicle features at night. The features of night and day are combined by fusing different convolutional layers to produce enhanced feature (EF) maps. Second, the OD module, based on the existing object detection network, is improved by cascading with the FTE module to detect vehicles on the EF maps. The proposed FteGanOd method recognizes vehicles at night with greater accuracy by improving the contrast between vehicles and the background and by suppressing interference from ambient light. The proposed FteGanOd is validated on the Berkeley Deep Drive (BDD) dataset and our private dataset. The experimental results show that our proposed method can effectively enhance vehicle features and improve the accuracy of vehicle detection at night.
20 September 2023 in IEEE Transactions on Instrumentation and Measurement
Catenary is one of the most crucial parts of electrified railway system. How to detect the part defects of catenary in time and keep it in a stable and safe operation conditions are the main tasks for maintainance. The existing data-driven vision-based defect detection methods will face a big challenge that, there are many catenary parts and each part has several types of defects, but there are few defect sample images for each type of defect, which limits them in real applications. To alleviate this problem, a semantic label-enhanced variational autoencoder (VAE) method for catenary part defect detection, termed Defect VAE (DefVAE), is presented. The proposed method is based on a label-enhanced VAE network that determines the distribution boundary in latent feature space of defect sample for additional defect generation. The addition of semantic label information to the VAE improves the inter-class distance in latent space, clarifying the boundary and further boosting the capabilities of the defect detection method, which is demonstrated in our experiments. Additionally, the defect type is classified by combining the outputs of the classifier confidence and the pixel-level reconstruction error which is based on a sliding label mode of the variational autoencoder. Extensive experiments with the open benchmark dataset MVTec and the catenary dataset collected by ourselves demonstrate that the presented DefVAE outperforms the baseline methods across the majority of indicators.
4 July 2025 in Computer Vision and Image Understanding
18 January 2021 in IEEE Access
The cross-view image translation task is aimed at generating scene images from arbitrary views. However, due to the great differences in the shapes and contents of the various views, the quality of the generated images is degraded. Small objects, such as vehicles’ shapes and details, are not clear, which causes them to be structurally inconsistent with the semantic map used to guide the generation process. To solve this problem, we propose a novel generative adversarial network based on a local and global information processing module (LAGGAN) to recover the image’s details and structures. The network will further combine the input viewpoint image and the target semantic segmentation map to guide the generation of the target image from another viewpoint. The proposed LAGGAN includes a two-stage generator and a parameter-sharing discriminator. LAGGAN uses a new local and global information processing module (LAG) to generate high-quality images from various views. Moreover, we integrate dilated convolutions into the discriminator to capture the global context, which can enhance the discriminative ability and further adjust the LAG module. Therefore, most semantic information can be preserved, and the details of the target viewpoint images can be translated more sharply. Quantitative and qualitative evaluation on both CVUSA and Dayton datasets attest to the fact that our method, LAGGAN, presents satisfactory perceptual results and is comparable to state-of-the-art methods on the cross-view image translation task.