Traffic incident detection based on a global trajectory spatiotemporal map

Traffic incidents endanger the smooth running of vehicles. Congestion caused by traffic incidents has caused a waste of time and fuel and seriously affected transportation efficiency. At present, most methods use manual judgment or image features to detect traffic incidents, but these methods lack timeliness, leading to secondary incidents. For dangerous road sections such as ramp-free and long downhills, this paper proposes an algorithm to quickly detect traffic incidents based on a spatiotemporal map of vehicle trajectories. First, a vehicle dataset from the monitoring perspective is constructed, and an improved YOLOv4 detection algorithm is used to detect images organized as batches. Based on the detection result, the multi-object tracking method of vehicle speed prediction in key frames is used to obtain the vehicle trajectory. Then according to the vehicle trajectory obtained in a single scene, the vehicle trajectory is reidentified and associated in the continuous monitoring scene to construct a long-distance vehicle trajectory spatiotemporal map. Finally, according to the distribution and generation status of the trajectory in the spatiotemporal map, traffic incidents such as vehicle parking, vehicle speeding, and vehicle congestion are analyzed. Experimental results show that the proposed method greatly increases the speed of vehicle detection and tracking and obtains high mAP, MOTA, and MOTP indicators. The global spatiotemporal map constructed by trajectory reidentification can achieve high detection rates for traffic incidents, reduce the average elapsed time, and avoid the problems of the inaccuracy of analyzing image features.

Traffic Foreground Detection at Complex Urban Intersections Using a Novel Background Dictionary Learning Model

In complex urban intersection scenarios, due to heavy traffic and signal control, there are many slow-moving or temporarily stopped vehicles behind the stop lines. At these intersections, it is difficult to extract traffic parameters, such as delay and queue length, based on vehicle detection and tracking due to the dense and severe occlusion of vehicles. In this study, a novel background subtraction algorithm based on sparse representation is proposed to detect the traffic foreground at complex intersections to obtain traffic parameters. By establishing a novel background dictionary update model, the proposed method solves the problem that the background is easily contaminated by slow-moving or temporarily stopped vehicles and therefore cannot obtain the complete traffic foreground. Using the real-world urban traffic videos and the PV video sequences of i -LIDS, we first compare the proposed method with other detection methods based on sparse representation. Then, the proposed method is compared with other commonly used traffic foreground detection models in different urban intersection traffic scenarios. The experimental results show that the proposed method performs well in keeping the background model being unpolluted from slow-moving or temporarily stopped vehicles and has a good performance in both qualitative and quantitative evaluations.

Ambulance detection using image processing and neural networks

Ambulance Detection using Image Processing and Neural Network is a vehicle detection and tracking system, which recognizes the vehicle (i.e., Ambulance in this case) amidst the traffic congestion. Due to the fact from past few years, the range of vehicles usage of the road is growing each day that results in traffic congestion, for better management of this traffic this system is useful. Traffic Congestion, as mentioned above, can be observed at an ever-growing pace in countries like India and Thailand, where the roads’ width and length make it impossible to make a separate lane for the emergency vehicle (like that of ambulance); Hence making it hard for the vehicle to pass through the traffic at the earliest possible time. The Ambulance tracking system is activated at the mapped junctions and that program detects the ambulance coming close to it and turns the traffic light to Green for the next 15 seconds. Geocoding is the practice of transforming addresses (like a physical address) to location information (like longitude and latitude) that can be used to locate a label on a map or to mark a grid. They plan to provide ambulances with this software to make it easy to transform addresses into a programmable format for review and retrieval. This data is converted to a system that shows all the crossings it must pass to meet the endpoint.

Estimation of Lane-Level Traffic Flow Using a Deep Learning Technique

This paper proposes a neural network that fuses the data received from a camera system on a gantry to detect moving objects and calculate the relative position and velocity of the vehicles traveling on a freeway. This information is used to estimate the traffic flow. To estimate the traffic flows at both microscopic and macroscopic levels, this paper used YOLO v4 and DeepSORT for vehicle detection and tracking. The number of vehicles passing on the freeway was then calculated by drawing virtual lines and hot zones. The velocity of each vehicle was also recorded. The information can be passed to the traffic control center in order to monitor and control the traffic flows on freeways and analyze freeway conditions.