In order to improve the tracking failure caused by small-target pedestrians and partially blocked pedestrians in dense crowds in complex environments, a pedestrian target detection and tracking method for an intelligent vehicle was proposed based on deep learning. On the basis of the YOLO detection model, the channel attention module and spatial attention module were introduced and were joined to the back of the backbone network Darknet-53 in order to achieve weight amplification of important feature information in channel and space dimensions and improve the representation ability of the model for important feature information. Based on the improved YOLO network, the flow of the DeepSort pedestrian tracking method was designed and the Kalman filter algorithm was used to estimate the pedestrian motion state. The Mahalanobis distance and apparent feature were used to calculate the similarity between the detection frame and the predicted pedestrian trajectory; the Hungarian algorithm was used to achieve the optimal matching of pedestrian targets. Finally, the improved YOLO pedestrian detection model and the DeepSort pedestrian tracking method were verified in the same experimental environment. The verification results showed that the improved model can improve the detection accuracy of small-target pedestrians, effectively deal with the problem of target occlusion, reduce the rate of missed detection and false detection of pedestrian targets, and improve the tracking failure caused by occlusion.

In order to improve the active safety driving vehicle and alleviate the intension of driving fatigue, an intelligent control strategy of automobile cruise is put forward based on the throttle or braking pedal combined control adopting the fuzzy control theory. A fuzzy logic controller is presented, which consists of the two input variables, the deviation of the theoretical safe distance and relative distance and the relative velocity between the preceding vehicle and the cruise vehicle, and the single output variable, that is, the throttle opening or the braking pedal travel. Taking the test data of 1.6 L vehicle with auto-transmission as an example, the function on the intelligent cruise control system is simulated adopting MATLAB/Simulink aiming at different working conditions on the city road. The simulation results show that the control strategy possesses integrated capability of automated Stop & Go control, actively following the preceding vehicle on the conditions of keeping the safety distance and the constant velocity cruise. The research results can offer the theory and technology reference for setting dSPACE type and developing the integrated control product of automobile cruise system.

A fuzzy increment controller is designed aimed at the vibration system of automobile active suspension with seven degrees of freedom (DOF). For decreasing vibration, an active control force is acquired by created Proportion‐Integration‐Differentiation (PID) controller. The controller’s parameters are adjusted by a fuzzy increment controller with self‐modifying parameters functions, which adopts the deviation and its rate of change of the body’s vertical vibration velocity and the desired value in the position of the front and rear suspension as the input variables based on 49 fuzzy control rules. Adopting Simulink, the fuzzy increment controller is validated under different road excitation, such as the white noise input with four‐wheel correlation in time‐domain, the sinusoidal input, and the pulse input of C‐grade road surface. The simulation results show that the proposed controller can reduce obviously the vehicle vibration compared to other independent control types in performance indexes, such as, the root mean square value of the body’s vertical vibration acceleration, pitching, and rolling angular acceleration.

A region of interest (ROI) that may contain vehicles is extracted based on the composite features on vehicle’s bottom shadow and taillights by setting a gray threshold on vehicle shadow region and a series of constraints on taillights. In order to identify the existence of target vehicle in front of Advanced Driver Assistance System (ADAS) for the extracted ROI, a neural network recognizer of the Radial Basis Function (RBF) is found by extracting a series of parameters on the vehicle’s edge and region features. Using a large amount of collected images, the ROI that may contain vehicles is verified to be effective by extracting composite features of the shadow at the bottom of vehicle and taillights. Based on the positive and negative sample base of vehicles, the neural network recognizer is trained and learned, which can quickly realize network convergence. Furthermore, the vehicle can be effectively identified in the region of interest using the trained network. Test results show that the vehicle detection method based on multifeature extraction and recognition method based on RBF network have stable performance and high recognition accuracy.

To address the issues of missed detections and false detections of small target missed detections caused by dense occlusion in complex traffic environments, a non-maximum suppression method, Bot-NMS, is proposed to achieve accurate prediction and localization of occluded targets. In the backbone network of YOLOv7, the Ghost module, the ECA attention mechanism, and the multi-scale feature detection structure are introduced to enhance the network’s capacity to learn small target features. The SCSTD and KITTI datasets were used to train and test the improved YOLOv7 target detection network model. The results demonstrate that the improved YOLOv7 method significantly enhances the recall rate and detection accuracy of various targets. A multi-target tracking method based on target re-identification (ReID) is proposed. Utilizing deep learning theory, a ReID model for target identification is constructed to comprehensively capture global and foreground target features. By establishing the correlation cost matrix of the cosine distance and IoU overlap, the correlation between target detection objects, the tracking trajectory, and ReID feature similarity is realized. The VERI-776 vehicle re-identification dataset and MARKET1501 pedestrian re-identification dataset were used to train the proposed ReID model, and multi-target tracking performance comparison experiments were conducted on the MOT16 dataset. The results show that the multi-target tracking method by introducing the ReID model and improving the cost matrix can better deal with the dense occlusion of the target, and can effectively and accurately track the road target in the realistic complex traffic environment.

Traffic flow characteristics are analyzed based on the representative site data collected from Beijing urban expressway. On the basis of the characteristics, the local on-ramp metering rate is determined by the comprehensive control effects from two parameters adopting time occupancy and speed as control variable to realize feedback control. In order to validate the feasibility of the method, we make use of VISSIM to validate this method by video survey data between Sitong Bridge and Lianxiang Bridge in North Ring. The simulation result shows that the method can improve average speed on mainline upstream at on-ramp about 7% and decreases the travel time on mainline section by 9.5% compared with un-signal control mode. It denotes that the method is feasible and can offer reference for the theory of ramp control and application in engineering practices.