Efficient vehicle detection with adaptive scan based on perspective geometry

In this paper, an efficient vehicle detection and tracking algorithm for detection incident in tunnel is proposed. The proposed algorithm consists of three steps. The first one is a step for background estimates, low computational complexity and memory consumption Running Gaussian Average (RGA) is used. The second step is vehicle detection step, Adaboost algorithm is applied to this step. In order to reduce false detection from a relatively remote location of the vehicles, local features according to height of vehicles are used to detect vehicles. If the local features of an object are more than the threshold value, the object is classified as a vehicle. The last step is a vehicle tracking step, the Kalman filter is applied to track moving objects. Through computer simulations, the proposed algorithm was found that useful to detect and track vehicles in the tunnel.

Advanced Driver Assistance Systems (ADAS) and Collision Avoidance Systems (CAS) are the primary modules of modern human-centric and autonomous driving applications, such as forward and rear-end collision warnings. To enhance the performance of ADAS and CAS systems in foggy weather, an Efficient and Cost-Effective Vehicle Detection and Tracking with Driver Assistance (ECE-VDTDA) system is proposed. The proposed ECE-VDTDA system comprises vehicle detection, tracking, and driver assistance modules. An optimized SimYOLO-V5s_WIOU vehicle detection algorithm is proposed, based on the SimSPPF module, the baseline You Only Look Once (YOLO) algorithm (YOLO-V5s), and the Wise Intersection Over Union (WIOU) localization loss function. State-of-the-art Deep-SORT, Strong-SORT, and optimized Deep-SORT algorithms are utilized for vehicle tracking. The vehicle detection and tracking performance of the ECE-VDTDA system is rigorously evaluated on DAWN, foggy driving, foggy cityscapes, BDD100K, web-collected, and self-collected foggy weather datasets. Optimized SimYOLO-V5s_WIOU algorithm outperformed on the foggy driving dataset with a 17.45% increase in mAP50, and foggy cityscapes dataset with a 0.32%, 1.05%, 1.58%, 2%, 0.54% increase in the multiclass mAP50, mAP50-95, F1 score, precision, and recall scores, respectively, compared to the baseline YOLO-V5s. Furthermore, the SimYOLO-V5s_WIOU algorithm also outperformed the state-of-the-art methods and enables Deep-SORT, Strong-SORT, and optimized Deep-SORT vehicle tracking algorithms to track vehicles with high confidence. The driver assistance module of the ECE-VDTDA system helps prevent imminent road collisions in foggy weather by estimating distance, speed, and time-to-collision and by issuing timely collision warnings. The experimental results demonstrate the robustness and computational efficiency of the proposed ECE-VDTDA system.

Vehicles detection in aerial images has a wide range of applications for visual surveillance. This paper introduces a framework for robust on-road vehicle detection. A passively trained framework system is built using conventional supervised learning. The strategy which is proposed for detecting vehicles is From-coarse-to-fine. In the first step. Road is segmented with LSD algorithm to narrow the area which will be detected. AdaBoost based algorithm is used for coarse detection. SVM is used to reduce false rates. Experimental results show that this framework yields a efficient and robust on-board vehicle detection system with high precision and low false rates.

State-of-the-art (SoTA) object detection models and their accuracy have been improved by a large margin via CNNs (Convolutional Neural Networks); however, these models still perform poorly for small road objects. Moreover, the SoTA models are mainly trained on public benchmark datasets such as MS COCO, which include more complicated backgrounds and thus make them robust for object detection. However, for surveillance or road videos, their monotone backgrounds make these SoTA detectors background-over-fitted. In applications such as autonomous driving or traffic flow estimation, the background-over-fitting problem will increase various challenges and lead to accuracy degradation in object detection. One novelty of this paper is to propose an MBA (Mixed Background Augmentation) method to improve detection accuracy without adding new labeling efforts and any pre-training processes. During the inference stage, only one input image is needed for vehicle detection without involving background subtraction. Another novelty of this paper is the design of an efficient MSP (Mixed Stage Partial) network to detect objects more accurately and efficiently from surveillance videos. Extensive experiments on KITTI and UA-DETRAC benchmarks show that the proposed method achieves the SoTA results for highly accurate and efficient vehicle detection. The detection accuracy is improved from 78.53% to 83.59% with 25.7 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$fps$ </tex-math></inline-formula> on the UA-DETRAC data set. The implementation code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/pingyang1117/MSPNet</uri> .

As the number of vehicles on roads, expressways, and highways grows rapidly, efficient vehicle detection, classification, tracking and counting have become essential to the civilian, military, and governmental uses like highway monitoring, toll collection, traffic planning and flow regulation. Vehicle detection is one of the most important of these tasks, which can help in enabling effective traffic management. A solution to this is a Computer Vision (CV)based approach, which can be implemented without interfering with traffic and allows the adaption of the system. The paper is an introduction of a cost-efficient and mobile system based on CV methods to identify and count vehicles in real-time. The system works with the video frames to detect the moving vehicles with the help of background subtraction, which is followed by additional processing that groups the vehicles into the groups of light vehicles, heavy vehicles, and motorcycles.

This paper presents a lightweight and efficient vehicle detection and tracking method for smart intersection environments using a low-cost, low-resolutionFMCW(Frequency Modulated Continuous Wave) LiDAR(Light Detecting And Ranging) sensor.We propose a framework that leverages Doppler-based velocity information fromFMCWLiDAR to facilitate point cloud accumulation. This leads to more effective background removal and robust multi-object tracking, even with low-resolution LiDAR data. The point cloud accumulation technique compensates for the sparsity of points representing vehicles by leveraging the radial velocity of detected points, resulting in denser and more accurate representations of vehicles. Background removal and lane segmentation are applied to effectively remove static objects and improve detection accuracy. The Kalman filter incorporates both position and velocity information of detected objects, enabling reliable tracking even when frame rates are low or objects move rapidly. The overall system is designed for real-time operation on edge devices, making it suitable for deployment in practical smart city scenarios. Experimental validation using real-world road data demonstrates that the proposed method significantly enhances detection and tracking performance compared to conventional approaches.

Real-time automatic detection and tracking of moving vehicles in videos acquired by airborne cameras is a challenging problem due to vehicle occlusion, camera movement, and high computational cost. This paper presents an efficient and robust real-time approach for automatic vehicle detection and tracking in aerial videos that employ both detections and tracking features to enhance the final decision. The use of Top-hat and Bottom-hat transformation aided by the morphological operation in the detection phase has been adopted. After detection, background regions are eliminated by motion feature points’ analysis of the obtained object regions using a combined technique between KLT tracker and K-means clustering. Obtained object features are clustered into separate objects based on their motion characteristic. Finally, an efficient connecting algorithm is introduced to assign the vehicle labels with their corresponding cluster trajectories. The proposed method was tested on videos taken in different scenarios. The experimental results showed that the recall, precision, and tracking accuracy of the proposed method were about 95.1 %, 97.5%, and 95.2%, respectively. The method also achieves a fast processing speed. Thus, the proposed approach has superior overall performance compared to newly published approaches.

Vehicle detection in aerial images has attracted great attention as an approach to providing the necessary information for transportation road network planning and traffic management. However, because of the low resolution, complex scene, occlusion, shadows, and high requirement for detection efficiency, implementing vehicle detection in aerial images is challenging. Therefore, we propose an efficient and scene-adaptive algorithm for vehicle detection in aerial images using an improved YOLOv3 framework, and it is applied to not only aerial still images but also videos composed of consecutive frame images. First, rather than directly using the traditional YOLOv3 network, we construct a new structure with fewer layers to improve the detection efficiency. Then, since complex scenes in aerial images can cause the partial occlusion of vehicles, we construct a context-aware-based feature map fusion to make full use of the information in the adjacent frames and accurately detect partially occluded vehicles. The traditional YOLOv3 network adopts a horizontal bounding box, which can attain the expected detection effects only for vehicles with small length–width ratio. Moreover, vehicles that are close to each other are liable to cause lower accuracy and a higher detection error rate. Hence, we design a sloping bounding box attached to the angle of the target vehicles. This modification is conducive to predicting not only the position but also the angle. Finally, two data sets were used to perform extensive experiments and comparisons. The results show that the proposed algorithm generates the desired and excellent performance.

This research focuses on assessing and developing a real-time detection system using the YOLOv8 algorithm. Accurate and fast vehicle detection is a big challenge in modern traffic management, especially in various environmental conditions such as bad weather, low lighting, and high traffic density. The aim of this study was to evaluate the performance of YOLOv8 under these conditions and identify potential improvements. The dataset used consists of 16,990 vehicle images with various variations and environmental conditions. After being trained, the model is evaluated using metrics such as precision, recall, and F1-score, as well as Intersection over Union (IoU) with a threshold of 0.8 on IoU. The results show that YOLOv8 is superior with a fairly high detection accuracy of 78%, with precision of 82% and recall above 90%, and is able to detect vehicles in real-time conditions. However, the challenge of detecting small objects or irregularly shaped vehicles such as tractors still needs to be optimized. This research also compared the performance of YOLOv8 with the SSD (Single Shot Detector) algorithm, where YOLOv8 was proven to be superior in terms of accuracy, precision, recall and F1-score. The research results obtained provide valuable insights for the development of traffic management systems based on deep learning technology. The main contribution of this research is to provide a more efficient and effective vehicle detection solution, which can be applied in modern traffic management systems. Thus, it is hoped that the results of this research can increase the efficiency of traffic management and have a positive impact on the development of intelligent transportation systems in the future.

An Efficient Vehicle Detection and Shadow Removal Using Gaussian Mixture Models with Blob Analysis for Machine Vision Application

We developed a low-cost, high-precision monocular visual ranging system based on the You Only Look Once version 5 (YOLOv5) object detection algorithm, addressing the limitations of traditional methods by integrating deep learning with computer vision.The YOLOv5 architecture is optimized through the adoption of the cross stage partial darknet backbone network and the Mosaic data augmentation strategy.The architecture improves vehicle detection accuracy with a mean average precision at intersection over union threshold 0.5 of 0.5719, and the inference speed of 140 frames per second.Multiscale object detection capabilities are further enhanced using an adaptive anchor box generation mechanism.The monocular ranging model was constructed by combining camera calibration parameters with perspective geometry principles.Bounding box information produced by YOLOv5 is mapped to three-dimensional spatial distances through the relationship between object pixel dimensions and actual physical dimensions, effectively mitigating the scale ambiguity inherent in monocular vision.The experimental results showed that the system maintained average ranging errors within engineering-acceptable limits under diverse lighting and weather conditions while satisfying real-time requirements.Compared with traditional geometric ranging benchmarks, the optimized model showed a 12% improvement in mean absolute error and root mean square error with an overall accuracy enhancement of 16.88%.The results confirm that the developed monocular visual ranging model balances cost and performance and is a reliable method for intelligent transportation systems.By functioning as a robust software-defined virtual sensor, the system offers significant engineering application value and contributes to the advancement of intelligent driving technologies.

Collision Avoidance Systems (CASs) are attracting a lot of attention as one of the most preferred solutions for advanced driver assistance and autonomous driving. However, scene understanding, which is an essential functionality in CASs, remains a major challenge mainly due to the need for real-time understanding of highly dynamic and complex environment. In this research, a number of robust and low complexity vision based scene understanding techniques for collision avoidance on roadway have been proposed. It has been well recognized in the literature that road surface detection in a dynamic environment is both challenging and computationally intensive. An efficient non-parametric road surface detection algorithm that exploits the depth cue is proposed to overcome the limitations of existing road surface detection methods. Unlike existing methods that attempt to fit the road surface into rigid models, the proposed method results in low computational complexity, mainly due to the reliance on four intrinsic road scene attributes observed under stereo geometry. It has been demonstrated that the proposed method is capable of detecting both planar and non-planar road surfaces. Extensive experimental results using three challenging benchmarks (i.e. enpeda, KITTI stereo/flow, and Daimler) show that the proposed road surface detection algorithm outperforms the baseline algorithms both in terms of detection accuracy (up to 23.12%) and runtime performance (up to 95.00%). Next, robust and low complexity algorithm for computing the ego-vehicle’s motion state is proposed. The proposed method estimates the ego-motion of the vehicle by first employing a novel pruning technique to reduce the computational complexity of the corner feature detection process without compromising on the quality of the extracted corner features. A robust and compute-efficient KLT tracker is proposed to facilitate the generation of the feature correspondences. Finally, an early RANSAC termination condition is introduced to the Gaussian-Newton optimization scheme to achieve rapid convergence of the motion estimation process. Evaluations based on the KITTI odometry benchmark show that the proposed visual odometry method outperforms the baseline algorithms both in terms of accuracy (up to 48.36%) and runtime performance. In addition, the proposed algorithm is placed among the top 15% when evaluated using the well-known KITTI odometry platform. Methods for robust and low complexity stereo-vision based obstacle detection and tracking are proposed. Unlike the works that focus only on the detection of vehicles or pedestrians, the proposed obstacle detection method relies on u-v disparity space to detect all obstacles in the scene. A Space of Interest (SOI) is defined to greatly reduce the search space of obstacles prior to employing adaptive hysteresis thresholding and connected component labeling techniques to segment SOI into sets of obstacles. Method for tracking obstacles across frames is also proposed by constructing a distinctive object appearance model. A number of strategies to further increase the distinctiveness and reduce the computational complexity for constructing the object model are also adopted. Finally, an online multi-object tracking framework is proposed by integrating the obstacle detection and data association modules in a robust way. Evaluations using the KITTI tracking benchmark confirm that the proposed obstacle detection and tracking method outperforms the baseline algorithm in terms of tracking accuracy by up to 51.78%. In addition, compared to the baseline algorithm that achieves about 0.23 frame per second (fps), the proposed method lends well for real-time performance with 20 fps. Finally, an efficient and robust risk assessment framework is proposed by integrating the obstacle detection and tracking, and visual odometry methods proposed in this thesis. The Extended Kalman Filter is customized to enhance the robustness of the predicted trajectory of the obstacles for assessing the collision risk. The robustness of collision prediction has been enhanced by accommodating positioning uncertainty. Evaluations based on the KITTI tracking dataset demonstrate that the proposed method are capable of robust and efficient assessment of the collision risk in diverse traffic scenarios. The proposed vision based scene understanding techniques in this research have paved the way towards realizing a real-time capable collision avoidance system that is both affordable and dependable.

Rapid and precise vehicle recognition and classification are essential for intelligent transportation systems, and road target detection is one of the most difficult tasks in the field of computer vision. The challenge in real-time road target detection is the ability to properly pinpoint relatively small vehicles in complicated environments. However, because road targets are prone to complicated backgrounds and sparse features, it is challenging to detect and identify vehicle kinds fast and reliably. We suggest a new vehicle detection model called MEB-YOLO, which combines Mosaic and MixUp data augmentation, Efficient Channel Attention (ECA) attention mechanism, Bidirectional Feature Pyramid Network (BiFPN) with You Only Look Once (YOLO) model, to overcome this problem. Four sections make up this model: Input, Backbone, Neck, and Prediction. First, to improve the detection dataset and strengthen the network, MixUp and Mosaic data improvement are used during the picture processing step. Second, an attention mechanism is introduced to the backbone network, which is Cross Stage Partial Darknet (CSPDarknet), to reduce the influence of irrelevant features in images. Third, to achieve more sophisticated feature fusion without increasing computing cost, the BiFPN structure is utilized to build the Neck network of the model. The final prediction results are then obtained using Decoupled Head. Experiments demonstrate that the proposed model outperforms several already available detection methods and delivers good detection results on the University at Albany DEtection and TRACking (UA-DETRAC) public dataset. It also enables effective vehicle detection on real traffic monitoring data. As a result, this technique is efficient for detecting road targets.

There are now available a wide variety of electronic imaging techniques for producing images and spatially-resolved spectra in the far- and middle-ultraviolet wavelength ranges below 300 nm. These are basically similar to techniques used in the near-UV and visible. They include devices with electronic readout, and those whose final images are produced on film. Radiometric imaging, however, requires special consideration of the photometric qualities of the sensor and means for calibrating the images- that is, correlating some measure of image intensity to the intensity or integrated flux of input radiation. As is true in most other wavelength ranges, calibration techniques can be based on (a) standard light sources, whose intensities vs. wavelength are known, or (b) standard comparison detectors, whose detection efficiencies vs. wavelength are known. Our group at NRL has been developing ultraviolet cameras and spectrographs, for space science and for DoD applications, primarily for the far-ultraviolet (below 200 nm) range. These record images electrographically (on electron-sensitive film) or electronically (using electron-bombarded CCD arrays). Our calibration techniques are primarily based on standard detectors, including calibrated photodiodes and windowless gas photoionization chambers, although we have occasionally used the SURF facility at NBS as a standard light source.

On-Road Vehicles Detection Based on LBP Derivatives Fusion