In traffic accidents, motorcycle accidents are the main cause of casualties, especially in developing countries. The main cause of fatal injuries in motorcycle accidents is that motorcycle riders or passengers do not wear helmets. In this paper, an automatic helmet detection of motorcyclists method based on deep learning is presented. The method consists of two steps. The first step uses the improved YOLOv5 detector to detect motorcycles (including motorcyclists) from video surveillance. The second step takes the motorcycles detected in the previous step as input and continues to use the improved YOLOv5 detector to detect whether the motorcyclists wear helmets. The improvement of the YOLOv5 detector includes the fusion of triplet attention and the use of soft‐NMS instead of NMS. A new motorcycle helmet dataset (HFUT‐MH) is being proposed, which is larger and more comprehensive than the existing dataset derived from multiple traffic monitoring in Chinese cities. Finally, the proposed method is verified by experiments and compared with other state‐of‐the‐art methods. Our method achieves mAP of 97.7%, F1‐score of 92.7% and frames per second (FPS) of 63, which outperforms other state‐of‐the‐art detection methods.

Vehicle model recognition is a typical fine-grained classification task that has a wide range of application prospects in safe cities and constitutes a research hotspot in the field of computer vision. Vehicles in images can appear at various angles, resulting in large differences in appearance. The existence of “multiviews” renders vehicle model recognition challenging. Recent research on vehicle model recognition has not fully explored the pose information of vehicles in different images, resulting in low model performance. In this study, we use vehicle pose information to solve the multiview vehicle model recognition (MV-VMR) problem and design a convolutional neural network (CNN) model with embedded vehicle pose information, known as the embedding pose CNN (EP-CNN). The proposed model includes two subnetworks: the pose estimation subnetwork (PE-SubNet) and vehicle model classification subnetwork (VMC-SubNet). PE-SubNet extracts the vehicle pose information, including the pose features and vehicle viewpoint. In VMC-SubNet, considering the scale variation of vehicles, an improved squeeze-and-excitation (SE) block, named the MultiSE block is implemented. We embed the vehicle viewpoint into the MultiSE block, which reweighs each channel such that the extracted features elicit different responses to different viewpoints. Subsequently, the pose features and classification features are integrated for classification. Experiments are conducted on the benchmark CompCars web-nature and Stanford Cars datasets. The results demonstrate that the proposed EP-CNN method can achieve higher recognition accuracy than most classic CNN models and several state-of-the-art fine-grained vehicle model classification algorithms. Code has been made available at: https://github.com/HFUT-CV/EP-CNN .

Due to the inherent limitations of camera sensors in capturing adequate light under low-light conditions, images often suffer from various degradation issues, such as illumination imbalances, artifacts, and noise. While generative model-based methods have made remarkable progress in low-light image enhancement (LLIE), they still face challenges such as unstable training and inconsistent generation quality. To address these challenges, we introduce MCLL-Diff, a novel multiconditional LLIE method based on diffusion probabilistic model (DPM). MCLL-Diff retains the forward process of DPM but introduces a unique multiconditional noise predictor (MCNP) in the reverse process. We first propose a learnable operator module (LOM) to enrich the prior knowledge incorporated in the reverse process. Then, we use MCNP to effectively integrate prior knowledge, low-light images, intermediate variables, and time steps to accurately predict noise. To validate the effectiveness of MCLL-Diff in high-level computer vision tasks, we construct a large-scale nighttime vehicle model (NVM) dataset from real-world nighttime street scenarios. Extensive experiments on benchmark datasets demonstrate MCLL-Diff’s superiority in both generalization performance and visual quality. Specifically, we achieved a significant improvement of 0.1 dB in peak signal-to-noise ratio (PSNR) metric on the VE-LOL dataset, and a notable increase of 0.76% in Top-1 accuracy when applied to object recognition on the NVM dataset.

Offline Multiple Appropriate Facial Reaction Generation (OMAFRG) aims to predict the reaction of different listeners given a speaker, which is useful in the senario of human-computer interaction and social media analysis. In recent years, the Offline Facial Reactions Generation (OFRG) task has been explored in different ways. However, most studies only focus on the deterministic reaction of the listeners. The research of the non-deterministic (i.e. OMAFRG) always lacks of sufficient attention and the results are far from satisfactory. Compared with the deterministic OFRG tasks, the OMAFRG task is closer to the true circumstance but corresponds to higher difficulty for its requirement of modeling stochasticity and context. In this paper, we propose a new model named FRDiff to tackle this issue. Our model is developed based on the diffusion model architecture with some modification to enhance its ability of aggregating the context features. And the inherent property of stochasticity in diffusion model enables our model to generate multiple reactions. We conduct experiments on the datasets provided by the ACM Multimedia REACT2023 and obtain the second place on the board, which demonstrates the effectiveness of our method.

In this paper, we present a novel learning-based scheme for vehicle logo recognition (VLR). This scheme is termed Multilayer Pyramid Network Based on Learning (MLPNL) and is based on the principle that considering multiple resolutions is helpful for extracting valuable features that benefit the final recognition performance. The innovations of this scheme include (1) a multilayer pyramid network, with pixel difference matrices (PDMs) as its input and output and feature parameters mapping one PDM to another; (2) an objective function and a corresponding optimization method designed to facilitate the learning of the feature parameters of the proposed multilayer pyramid network; and (3) a multi-codebook-based encoding method that makes best use of the features extracted from PDMs corresponding to different resolutions. Extensive experiments conducted with an open dataset, HFUT-VL, demonstrate that the proposed MLPNL scheme outperforms state-of-the-art handcrafted descriptors and non-deep-learning-based learning methods when fewer training samples exist. Experiments conducted with a benchmark dataset, XMU, demonstrate that MLPNL outperforms existing state-of-the-art VLR methods. Experiments conducted both on HFUT-VL and XMU demonstrate that MLPNL is faster than most deep-learning-based learning methods while maintaining nearly the same recognition rate. Code has been made available at: https://github.com/HFUT-CV/MLPNL.