VV-YOLO: A Vehicle View Object Detection Model Based on Improved YOLOv4.

Vehicle view object detection technology is the key to the environment perception modules of autonomous vehicles, which is crucial for driving safety. In view of the characteristics of complex scenes, such as dim light, occlusion, and long distance, an improved YOLOv4-based vehicle view object detection model, VV-YOLO, is proposed in this paper. The VV-YOLO model adopts the implementation mode based on anchor frames. In the anchor frame clustering, the improved K-means++ algorithm is used to reduce the possibility of instability in anchor frame clustering results caused by the random selection of a cluster center, so that the model can obtain a reasonable original anchor frame. Firstly, the CA-PAN network was designed by adding a coordinate attention mechanism, which was used in the neck network of the VV-YOLO model; the multidimensional modeling of image feature channel relationships was realized; and the extraction effect of complex image features was improved. Secondly, in order to ensure the sufficiency of model training, the loss function of the VV-YOLO model was reconstructed based on the focus function, which alleviated the problem of training imbalance caused by the unbalanced distribution of training data. Finally, the KITTI dataset was selected as the test set to conduct the index quantification experiment. The results showed that the precision and average precision of the VV-YOLO model were 90.68% and 80.01%, respectively, which were 6.88% and 3.44% higher than those of the YOLOv4 model, and the model's calculation time on the same hardware platform did not increase significantly. In addition to testing on the KITTI dataset, we also selected the BDD100K dataset and typical complex traffic scene data collected in the field to conduct a visual comparison test of the results, and then the validity and robustness of the VV-YOLO model were verified.

Multi-modality trajectory prediction with the dynamic spatial interaction among vehicles under connected vehicle environment.

Compared to non-connected vehicle environments, the connected vehicle environment establishes vehicle interconnection through communication technologies, resulting in more complex interaction, network topologies, and large-scale inputs. This complexity renders traditional trajectory prediction models, which rely primarily on inputting historical information of the target vehicle, inadequate for handling the complex and dynamic interactive lane-changing scenarios in connected vehicle environments. In a connected vehicle environment, it is necessary to propose a more targeted and stable lane-changing behavior prediction method based on vehicle traveling characteristics. Taking into account dynamic spatial interaction among vehicles, this study proposes a multi-modality trajectory prediction model called STA-LSTM to perform analysis on the potential interactive behaviors among vehicles under connected vehicle lane-changing scenarios, and specifically to expand the multi-modality feature input of the vehicle trajectory prediction model. The spatial grid occupancy method is used to model the interactions between vehicles. A space-dimensional attention mechanism is introduced to adaptively match the influencing weights of the surrounding vehicles with the target vehicle and to improve the interactive information extraction method. In addition, the attention module is incorporated into the LSTM decoder from the time dimension so that the established model can identify significant historical hidden features during each trajectory decoding process. To account for the uncertainty of trajectory prediction, the vectors of vehicle interactions are incorporated into contextual information to improve the reliability of prediction results and the robustness of the established model. Compared with conventional baseline models, the proposed model exhibited lower root mean square error (RMSE) and negative log-likelihood (NLL) values, and the RMSE values at different prediction times of 1s, 2s, 3s, 4s, and 5s are 0.46m, 1.15m, 1.89m, 2.84m, and 4.05m, respectively. This indicates that the proposed model can accurately predict the interactions between vehicles and the travel paths of surrounding target vehicles.

License plate recognition algorithm for passenger cars in Chinese residential areas.

This paper presents a solution for the license plate recognition problem in residential community administrations in China. License plate images are pre-processed through gradation, middle value filters and edge detection. In the license plate localization module the number of edge points, the length of license plate area and the number of each line of edge points are used for localization. In the recognition module, the paper applies a statistical character method combined with a structure character method to obtain the characters. In addition, more models and template library for the characters which have less difference between each other are built. A character classifier is designed and a fuzzy recognition method is proposed based on the fuzzy decision-making method. Experiments show that the recognition accuracy rate is up to 92%.

Research on safety evaluation model for in-vehicle secondary task driving.

This paper presents a new method for evaluating in-vehicle secondary task driving safety. There are five in-vehicle distracter tasks: tuning the radio to a local station, touching the touch-screen telephone menu to a certain song, talking with laboratory assistant, answering a telephone via Bluetooth headset, and finding the navigation system from Ipad4 computer. Forty young drivers completed the driving experiment on a driving simulator. Measures of fixations, saccades, and blinks are collected and analyzed. Based on the measures of driver eye movements which have significant difference between the baseline and secondary task driving conditions, the evaluation index system is built. The Analytic Network Process (ANP) theory is applied for determining the importance weight of the evaluation index in a fuzzy environment. On the basis of the importance weight of the evaluation index, Fuzzy Comprehensive Evaluation (FCE) method is utilized to evaluate the secondary task driving safety. Results show that driving with secondary tasks greatly distracts the driver's attention from road and the evaluation model built in this study could estimate driving safety effectively under different driving conditions.

Decomposition of NO in automobile exhaust by plasma-photocatalysis synergy.

The combination of plasma discharge and TiO2 photocatalysis exhibits high performances in the removal of nitrogen monoxide (NO). This article is aimed at elucidating the relationships between NO decomposition efficiency and various experimental parameters, including voltages, humidity and temperature. The experimental results indicate that the efficiency of NO removal by synergic plasma-catalyst coupling is significantly higher than plasma only or photocatalyst only systems. Moreover, the NO removal efficiency improves with the increase of applied voltage. Meanwhile, a higher humidity results in a reduced number of electron-hole pairs at the surface of TiO2 photocatalyst, leading to lower synergic purification efficiencies. Finally, the efficiency of NO removal is raised with the increase of temperature due to the fact that the adsorption of NO and water by nano-TiO2 is affected by environmental temperature.