Lévy flight is a random walk mechanism which can make large jumps at local locations with a high probability. The probability density distribution of Lévy flight was characterized by sharp peaks, asymmetry, and trailing. Its movement pattern alternated between frequent short-distance jumps and occasional long-distance jumps, which can jump out of local optimal and expand the population search area. The metaheuristic algorithms are inspired by nature and applied to solve NP-hard problems. Lévy flight is used as an operator in the cuckoo algorithm, monarch butterfly optimization, and moth search algorithms. The superiority for the Lévy flight-based metaheuristic algorithms has been demonstrated in many benchmark problems and various application areas. A comprehensive survey of the Lévy flight-based metaheuristic algorithms is conducted in this paper. The research includes the following sections: statistical analysis about Lévy flight, metaheuristic algorithms with a Lévy flight operator, and classification of Lévy flight used in metaheuristic algorithms. The future insights and development direction in the area of Lévy flight are also discussed.

/pdf/survey-of-levy-flight-based-metaheuristics-for-optimization-2s0seh9q.pdf

Survey of Lévy Flight-Based Metaheuristics for Optimization

Transportation safety has been widely discussed for avoiding forward collisions. The broad concept of remote sensing can be applied to detect the front of vehicles without contact. The traditional Haar features use adjacent rectangular areas for many ordinary vehicle studies to detect the front vehicle images in practice. This paper focused on large vehicles using a front-installed digital video recorder (DVR) with a near-infrared (NIR) camera. The views of large and ordinary vehicles are different; thus, this study used a deep learning method to process progressive improvement in moving vehicle detection. This study proposed a You Only Look Once version 4 (YOLOv4) supplemented with the fence method, called YOLOv4(III), to enhance vehicle detection. This method had high detection accuracy and low false omission rates using the general DVR equipment, and it provided comparison results. There was no need to have a high specification front camera, and the proposed YOLOv4(III) was found to have competitive performance. YOLOv4(III) reduced false detection rates and had a more stable frame per second (FPS) performance than with Haar features. This improved detection method can give an alert for large vehicle drivers to avoid serious collisions, leading to a reduction in the waste of social resources.

/pdf/enhancing-front-vehicle-detection-in-large-vehicle-fleet-266jy3ua.pdf

Enhancing Front-Vehicle Detection in Large Vehicle Fleet Management

ShortYOLO-CSP: a decisive incremental improvement for real-time vehicle detection

Traditional machine learning approaches are susceptible to factors such as object scale, occlusion, leading to low detection efficiency and poor versatility in vehicle detection applications. To tackle this issue, we propose a part-aware refinement network, which combines multi-scale training and component confidence generation strategies in vehicle detection. Specifically, we divide the original single-valued prediction confidence and adopt the confidence of the visible part of the vehicle to correct the absolute detection confidence of the vehicle. That reduces the impact of occlusion on the detection effect. Simultaneously, we relabel the KITTI data, adding the detailed occlusion information of the vehicles. Then, the deep neural network model is trained and tested using the new images. Our proposed method can automatically extract the vehicle features and solve larger error problems when locating vehicles in traditional approaches. Extensive experimental results on KITTI datasets show that our method significantly outperforms the state-of-the-arts while maintaining the detection time. 

/pdf/part-aware-refinement-network-for-occlusion-vehicle-2yk9x1zm.pdf

Part-Aware Refinement Network for Occlusion Vehicle Detection

Object detection is an essential technology in the computer vision domain and plays a vital role in intelligent transportation. Intelligent vehicles utilize object detection on images for environment perception. This work develops a target detection algorithm based on deep learning technologies, particularly convolutional neural networks and neural network modeling. Building on the analysis of the traditional Haar-like vehicle recognition algorithm, a vehicle recognition algorithm based on a convolutional neural network with fused edge features (FE-CNN) is proposed. The experimental results demonstrate that FE-CNN improves the recognition precision and the model’s convergence speed through a simple and effective edge feature fusion method. In the experiment conducted using real traffic scene for vehicle recognition, the developed algorithm achieves a 99.82% recognition rate in efficient time, demonstrating the capability for real-time performance and accurate target detection.

Deep learning-based algorithm for vehicle detection in intelligent transportation systems

Multilevel thresholding image segmentation has always been a popular issue and attracted the attention of many researchers in recent years since it has many applications. However, the process of determining the optimal thresholds in the case of multilevel thresholding is time-consuming. To address this problem, in this paper, the optimal thresholds for multilevel thresholding image segmentation are obtained by maximizing the Renyi entropy using the Levy flight firefly algorithm (FAFA), in which an adaptive parameter strategy based on Levy flight is used to improve the performance of the standard firefly algorithm (FA). The performance of the proposed algorithm has been evaluated using several benchmark images and has been compared with five different heuristic algorithms. The experimental results showed that the proposed algorithm prevailed over the other five competitive algorithms in terms of the objective function value, image quality measures, and computational efficiency.

Dongbo Zhang

Papers

Deep learning-based algorithm for vehicle detection in intelligent transportation systems

An adaptive Lévy flight firefly algorithm for multilevel image thresholding based on Rényi entropy