Complex Road Scenes Research Articles

DETECTION OF STREET LIGHT POLES IN ROAD SCENES FROM MOBILE LIDAR MAPPING DATA FOR ITS APPLICATIONS

Abstract. Identification of street light poles is very significant and crucial for intelligent transportation systems. Automatic detection and extraction of street light poles are a challenging task in road scenes. This is mainly because of complex road scenes. Nowadays mobile laser scanners have been used to acquire three-dimensional geospatial data of roadways over a large area at a normal driving speed. With respect to the high density of such data, new and beneficial algorithms are needed to extract objects from these data. In this article, our proposed algorithm for extraction of street light poles consists of five main steps: 1. Preprocessing, 2. Ground removal, 3. 3D connected components analysis, 4. Local geometric feature generation, 5. Extraction of street light poles using Bhattacharya distance metric. The proposed algorithm is tested on two rural roadways, called Area1 and Area2. Evaluation results for Area1 report 0.80, 0.72 and 0.62 for completeness, correctness and quality, respectively.

A Computationally Economic Novel Approach for Real-Time Moving Multi-vehicle Detection and Tracking toward Efficient Traffic Surveillance

Efficient and precise real-time video-based vehicles supervision systems for traffic surveillance are ever demanding. Developing an accurate detection and tracking algorithm by incorporating the effects of vehicles shadow or visual obstacles/occlusion including road signs, trees, or other vehicles is a challenging task. We propose a new approach for efficient detection and tracking of moving vehicles in the presence of shadow and partial occlusion under complex road scenes by combining the modified background subtraction and innovative adaptive search window methods. The use of variable-size window (Bounding Box) reduces the searching space proportional to the allocated time of the moving vehicles. First, a background model is constructed and then subtracted from subsequent traffic frames to distinguish the foreground objects (moving vehicles regions) and stable background regions. Finally, the shadow detection and occlusion handling between the moving vehicles are implemented to leverage the surveillance performance. The performance of the proposed method is benchmarked using baseline highway category of changedetection.net standard dataset having 1231 frames. Performance evaluation is carried out in terms of time complexity analysis, detection accuracy, and processing time. The experimental results demonstrate a radical reduction in computational time in terms of searched space. A superior detection accuracy (more than 99%), and processing time \(\sim \)29.6 ms (per frames in milliseconds) together with the time complexity degree of O(\(n^{2}\)), is achieved. Excellent features of these results suggest that the proposed approach is prospective for computer vision application and high-way traffic surveillance.

Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes

Vision-based road extraction is essentially important in many fields, such as for intelligent traffic and robot navigation. However, the road detection in urban or ill-structured roads is still very challenging at current stage, and the existing methods often suffer from high computational complexity. This paper reports a novel and efficient method for road detection in challenging scenes. First, the dark channel based image segmentation is proposed to distinguish a rough road region from complex background noise, which is envisioned to reduce the workload of road detection. Furthermore, instead of using the conventional pixel-wise soft voting, a new voting strategy based on the vanishing point and the properties of the segmented regions is proposed to further reduce the computation time of road extraction stage. Finally, the segmented region which has the maximum voting value is selected as the road region. Experimental results demonstrated that the proposed algorithm shows superior performance in different kinds of road scenes. It can remove the interference from pedestrians, vehicles and other obstacles. Our method is about 40 times faster in detection speed, when compared to a recently well-known approach.

Detection of vehicle approach in the presence of additional motion and simulated observer motion at road junctions.

One of the key contributory factors for accident involvement is the misjudgment of vehicle approach. Past research has indicated that individuals can use the rate of visual "looming" in order to judge the time to arrival (TTA) of approaching vehicles. Although a large number of road traffic collisions occur at roadside junctions, very little research has focused on individuals' abilities to detect the onset of visual looming within a complex road scene at junction scenarios. In this research, computer generated scenes with photorealistic vehicle images, and a psychophysical staircase methodology, were used to explore drivers' ability to detect the approach of both motorcycles and cars within a contextually rich city scene. Across three experiments the effect of additional vehicular and observer motion on driver detection of vehicle approach was assessed. Results showed that individuals were significantly poorer at detecting the approach of the motorcycle stimulus compared with the car stimulus. Results also showed that additional vehicular motion within the scene had a negative effect on detection thresholds for the car stimulus. Finally, the results showed that introducing lateral global motion of the scene, such as might occur if the observer was moving steadily forward from a junction, negatively affected detection thresholds. The theoretical implications of the findings are discussed, including how vehicles traveling at high speed are often below the threshold for detecting visual looming. Practical implications for road design and layout are discussed that address the perceptual errors noted.

A background subtraction algorithm for detecting and tracking vehicles

An innovative system for detecting and extracting vehicles in traffic surveillance scenes is presented. This system involves locating moving objects present in complex road scenes by implementing an advanced background subtraction methodology. The innovation concerns a histogram-based filtering procedure, which collects scatter background information carried in a series of frames, at pixel level, generating reliable instances of the actual background. The proposed algorithm reconstructs a background instance on demand under any traffic conditions. The background reconstruction algorithm demonstrated a rather robust performance in various operating conditions including unstable lighting, different view-angles and congestion.

Vision-based road-traffic monitoring sensor

Current techniques for road-traffic monitoring rely on sensors that have limited capabilities and are often both costly and disruptive to install. The use of video cameras (many of which are already installed to survey road networks), coupled with computer vision techniques, offers an attractive alternative to current sensors. Vision-based sensors have the potential to measure a greater variety of traffic parameters (e.g. entry/exit statistics, journey times and incident detection) while installation and maintenance may be performed without disruption to traffic flow. Work on a model based approach for locating vehicles in images of complex road scenes is presented. The location of the vehicle in the image is transformed to the vehicle's position and orientation in the real world while the deformable vehicle model allows the vehicle's principal dimensions to be measured. This data may be passed to a high level tracking algorithm to extract traffic parameters such as vehicle speed, vehicle count, and junction entry/exit statistics. The principal dimensions may be used to classify the vehicle within categories such as car, van or bus. The system could also be used as a boot-strap process for faster, but perhaps less robust, tracking algorithms. The key features of the system are described and results from testing it on images from real traffic scenes are presented.

Vehicle recognition and tracking from road image sequences

In this paper, synergies between the recognition and tracking processes for autonomous vehicle driving are studied. Object recognition is periodically performed to focus attention on specific parts of the visual signal and to assign them symbolic meanings. Tracking is used to maintain correspondences between objects identified at successive recognition instants as well as to provide further features (e.g., spatio-temporal trajectories) on which to base object-pose estimation. Results obtained by using complex road scenes are reported, which demonstrate the validity of the approach in terms of robustness, accuracy, and time responses.