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.

Image fusion aims at aggregating the redundant and complementary information in multiple original images, the most challenging aspect is to design robust features and discriminant model, which enhances saliency information in the fused image. To address this issue, the authors develop a novel image fusion algorithm for preserving the invariant knowledge of the multimodal image. Specifically, they formulate a novel unified architecture based on non‐subsampled contourlet transform (NSCT). Their method introduces Quadtree decomposition and Bezier interpolation to extract crucial infrared features. Furthermore, they propose a saliency advertising phase congruency‐based rule and local Laplacian energy‐based rule for low‐ and high‐pass sub‐bands fusion, respectively. In this approach, the fusion image could not only combine the local and global features of the source image to avoid smoothing the edge of the target, but also retain the minor scales details and resists the interference noise of the multi‐modal image. Both objective assessments and subjective visions of experimental results indicate that the proposed algorithm performs competitively in both objective evaluation criteria and visual quality.

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

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.

Semantic segmentation based on RGB and thermal images is an effective way to achieve an all-day understanding of road scenes. However, how to fuse the RGB and thermal information effectively remains an open problem. By studying fusion strategies at different stages, an illumination-aware feature fusion network has been developed for all-day semantic segmentation of urban road scenes in this paper, called IAFFNet. At the encoding stage, we introduce a bi-directional guided feature fusion module to effectively recalibrate and unify both RGB and thermal information. At the decoding stage, we have developed adaptive fusion modules to fuse low-level details and high-level semantic information. Finally, we have developed a decision-level illumination-aware strategy to achieve robust all-day segmentation. As far as we know, we are the first to incorporate illumination clues explicitly into RGB-T semantic segmentation. Extensive experimental evaluations demonstrate that the developed method can achieve remarkable performance on public datasets compared with state-of-the-art methods.