SSD Based Target Detection Algorithm for the Autonomous Driving Vision System

Autonomous driving is an important global research hotspot and a strategic direction of the development of the automobile industry. The autonomous driving module is inseparable from the support of the target detection technology. Its application in the field of autonomous driving is of great research significance. So with China network and Web of Science as a data source, with the help of CiteSpace visual analysis software for 2014-2021 international and domestic target detection algorithm application in the field of autonomous driving literature, in post trend analysis, keywords co-occurrence map, keyword clustering map, Timezone View, analysis, on the basis of the time distribution, research institutions, research hotspot, future trend prediction from several aspects of the statistics, comparison and analysis.

In recent years, with the progress of society and the development of the economy, the number of cars in China has been increasing. In wireless communication networks, the choice of wireless nodes has a greater impact on the improvement of system performance (such as channel capacity, coverage area, etc.). The intelligent vehicle target detection system can perceive and recognize the surrounding objects such as pedestrians and vehicles through sensors, which is the basis for realizing the unmanned driving of intelligent vehicles. In a wireless environment where multiple wireless nodes coexist, current research focuses on how long it takes to re-plan the selection of wireless nodes (for mobile environments) and how to allocate and manage wireless nodes, such as where under the conditions of wireless, who will wireless with whom, and in what way (such as auto focus, digital fusion, or other) wireless, etc.; the dedicated centralized controller (such as the base station of the infrastructure-based wireless access network) determines the wireless partner (i.e., centralized type selection), or the wireless node decides by itself (i.e., distributed selection); select the appropriate number of wireless nodes to take into account the system performance gain and implementation complexity. The popularity of automobiles has brought great convenience to people's lives, but it has also brought greater traffic pressure. At present, the amount of domestic automobile traffic has increased exponentially, and urban traffic congestion has become more serious, and even caused serious traffic accidents, directly affecting people's quality of life. The emergence of intelligent transportation systems has effectively alleviated road traffic pressure and reduced the incidence of traffic accidents. As an important part of the intelligent transportation system, the research of intelligent vehicles has received extensive attention. Intelligent vehicles use a variety of sensors installed on the body to sense the environment, and realize intelligent driving functions such as lane line detection, obstacle detection, dynamic cruise control, and unmanned driving, which is conducive to reducing the incidence of traffic accidents and improving the safety of vehicle driving. At present, in the research of target recognition and tracking of intelligent vehicles, the traditional target detection method is mainly based on artificial feature extraction, which is difficult to describe more complex or higher-order image features, and the tracking effect is not good, which limits the target detection. An intelligent vehicle is an intelligent system with functions such as environment perception, planning decision-making, and operation control, and is an important part of the intelligent transportation system. Identify the effect. In response to these problems, we present a study of the target recognition and tracking of intelligent vehicles based on grid map and lidar sensor technology. To verify the proposed method in the actual scene, we identify and track the vehicle ahead on the road through a car equipped with a lidar sensor. The meaning of target detection: target detection, also called target extraction, is an image segmentation based on target geometric and statistical features. The results show that the proposed research method can accurately identify the vehicle in front and detect the moving targets such as pedestrians. The tracking trajectory is also consistent with the expected route. The results show that the laser radar-based vehicle target recognition and tracking in this study is effective. In the 10 frames of images, the average time taken for the recognition of one frame of image is 9.8 ms, while the traditional method is 12.9 ms. Technology can improve reliable road information for intelligent vehicle driving and improve the transportation efficiency and safety performance of intelligent vehicles. There are two main target detection methods for lidar: detection methods based on feature extraction and detection methods based on grid maps.

Unmanned aerial vehicle (UAV) aerial images often present challenges such as small target sizes, high target density, varied shooting angles, and dynamic poses. Existing target detection algorithms exhibit a noticeable performance decline when confronted with UAV aerial images compared to general scenes. This paper proposes an outstanding small target detection algorithm for UAVs, named Fine-Grained Feature Perception YOLOv8s-P2 (FGFP-YOLOv8s-P2), based on YOLOv8s-P2 architecture. We specialize in improving inspection accuracy while meeting real-time inspection requirements. First, we enhance the targets’ pixel information by utilizing slice-assisted training and inference techniques, thereby reducing missed detections. Then, we propose a feature extraction module with deformable convolutions. Decoupling the learning process of offset and modulation scalar enables better adaptation to variations in the size and shape of diverse targets. In addition, we introduce a large kernel spatial pyramid pooling module. By cascading convolutions, we leverage the advantages of large kernels to flexibly adjust the model’s attention to various regions of high-level feature maps, better adapting to complex visual scenes and circumventing the cost drawbacks associated with large kernels. To match the excellent real-time detection performance of the baseline model, we propose an improved Random FasterNet Block. This block introduces randomness during convolution and captures spatial features of non-linear transformation channels, enriching feature representations and enhancing model efficiency. Extensive experiments and comprehensive evaluations on the VisDrone2019 and DOTA-v1.0 datasets demonstrate the effectiveness of FGFP-YOLOv8s-P2. This achievement provides robust technical support for efficient small target detection by UAVs in complex scenarios.

Target detection based on unmanned aerial vehicle (UAV) images has increasingly become a hot topic with the rapid development of UAVs and related technologies. UAV aerial images often feature a large number of small targets and complex backgrounds due to the UAV’s flying height and shooting angle of view. These characteristics make the advanced YOLOv4 detection method lack outstanding performance in UAV aerial images. In light of the aforementioned problems, this study adjusted YOLOv4 to the image’s characteristics, making the improved method more suitable for target detection in UAV aerial images. Specifically, according to the characteristics of the activation function, different activation functions were used in the shallow network and the deep network, respectively. The loss for the bounding box regression was computed using the EIOU loss function. Improved Efficient Channel Attention (IECA) modules were added to the backbone. At the neck, the Spatial Pyramid Pooling (SPP) module was replaced with a pyramid pooling module. At the end of the model, Adaptive Spatial Feature Fusion (ASFF) modules were added. In addition, a dataset of forklifts based on UAV aerial imagery was also established. On the PASCAL VOC, VEDAI, and forklift datasets, we ran a series of experiments. The experimental results reveal that the proposed method (YOLO-DRONE, YOLOD) has better detection performance than YOLOv4 for the aforementioned three datasets, with the mean average precision (mAP) being improved by 3.06%, 3.75%, and 1.42%, respectively.

Objective The effects of different algorithms on detecting and tracking moving objects in images based on computer vision technology are studied, and the best algorithm scheme is confirmed. Methods An automatic moving target detection and tracking algorithm based on the improved frame difference method and mean-shift was proposed to test whether the improved algorithm has improved the detection and tracking effect of moving targets. The algorithm improves the traditional three-frame difference method and introduces a single Gaussian background model to participate in target detection. The improved frame difference method is used to detect the target, and the position window and center of the target are determined. Combined with the mean-shift algorithm, it is determined whether the template needs to be updated according to whether it exceeds the set threshold so that the algorithm can automatically track the moving target. Results The position and size of the search window change as the target location and size change. The Bhattacharyya similarity measure ρ (y) exceeds the threshold r, and the target detection algorithm is successfully restarted. Conclusion The algorithm for automatic detection and tracking of moving objects based on the improved frame difference method and mean-shift is fast and has high accuracy.

There are two main approaches to hyperspectral target detection: anomaly detection techniques, which detect outliers substantially different from the background, and spectral signature techniques, which require as an input a user-defined target signature. Oftentimes, however, the target signature may not be known, or there may be unexpected targets in the image, which are unknown but still of interest. As a result, algorithms that can automatically extract potential target signatures without any a priori knowledge are of great interest. In this work, a fusion-based algorithm is developed that takes advantage of both spatial and spectral information to automatically extract the spectral signatures of potential targets of interest. The performance of several target detection algorithms is compared for both the proposed spatially-spectrally estimated (SSE) target signature and the initial target signature used by the Automatic Target Detection and Classification Algorithm (ATDCA). It is shown that the SSE signature leads to improved automatic spectral target recognition (ATSR) performance than the ATDCA algorithm for the test conducted on the AVIRIS Indian Pines dataset.

The advancement of autonomous driving systems hinges on accurate and reliable vehicle and lane detection. This paper presents an integrated method to improve autonomous driving systems by merging Histogram of Oriented Gradients (HOG)-based vehicle detection with Convolutional Neural Network (CNN)-based lane detection. HOG effectively identifies vehicles by capturing edge orientations and structural features, while CNNs excel in detecting intricate lane patterns through deep learning. The combination of these techniques offers a robust solution for detecting both vehicles and lanes, essential for autonomous navigation. Evaluated across a diverse dataset featuring various driving conditions, the system's performance is measured using precision, recall, F1 score (for vehicle detection), and accuracy (for lane detection). The results indicate significant enhancements in detection capabilities, leading to improved situational awareness and safer navigation. Future work will aim to refine the system further and tackle challenges in more complex driving environments, marking this approach as a promising advancement in autonomous driving technology.

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP and NGCTrack-based target detection and tracking algorithm to address these issues. Firstly, the performance of detecting small targets in occluded scenes is enhanced by adding a MODConv to the small-target detection head and increasing its size; In addition, excessive deletion of prediction boxes is prevented by utilizing LSKAttention mechanism to adaptively adjust the target sensing field at the downsampling stage and combining it with the Soft-NMS strategy. Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. At the target tracking stage, the so-called NGCTrack in our algorithm replaces IOU with GIOU and employs a modified NSA Kalman filter to adjust the state-space aspect ratio for width prediction. Finally, the camera adjustment mechanism was introduced to improve the precision and consistency of tracking. The experimental results show that, compared to YOLOv8, the YOLO-LMP model improves map50 and map50:95 metrics by 10.3 and 12.2%, respectively and the number of parameters is decreased by 47.7%. After combined it with the improved NGCTrack, the number of IDSW reduced by 73.6% compared to the ByteTrack method, while the MOTA and IDF1 increase by 5.2 and 9.8%, respectively.

This paper proposes an intelligent digital modeling system based on computer vision technology, aiming to realize real-time analysis and modeling of sports games. This study uses deep learning technology, combined with motion target detection and action recognition algorithms, to build an automated and intelligent sports game modeling system. The system captures game data in real time through video surveillance equipment, and uses target detection algorithms such as YOLO and SSD to identify athletes, balls and other game elements. At the same time, it realizes the accurate capture of athlete movements and tactical intentions based on the algorithm of posture estimation and action recognition. In terms of experimental verification, this paper takes football games as an example. The accuracy of the system in motion target detection is 92.5%, and the accuracy in athlete action recognition is 87.3<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>• In addition, the real-time modeling accuracy of the system is controlled within 5%, and the processing delay is less than 200 milliseconds, which meets the requirements of real-time analysis. Through the analysis of experimental results, this study proves the efficiency and accuracy of the system in complex sports game environments.

Target detection and segmentation algorithms have long been one of the main research directions in the field of computer vision, especially in the study of sea surface image understanding, these two tasks often need to consider the collaborative work at the same time, which is very high for the computing processor performance requirements. This article aims to study the deep learning sea target detection and segmentation algorithm. This paper uses wavelet transform-based filtering method for speckle noise suppression, deep learning-based method for land masking, and the target detection part uses an improved CFAR cascade algorithm. Finally, the best separable features are selected to eliminate false alarms. In order to further illustrate the feasibility of the scheme, this paper uses measured data and simulation data to verify the scheme and discusses the effect of different signal-to-noise ratio, sea target type, and attitude on the algorithm performance. The research data show that the deep learning sea target detection and segmentation algorithm has good detection performance and is generally applicable to ship target detection of different types and different attitudes. The results show that the deep learning sea target detection and segmentation algorithm fully takes into account the irregular shape and texture of the interfering target detected in the optical remote sensing image so that the accuracy rate is 32.7% higher and the efficiency is increased by about 1.3 times. The deep learning sea target detection is compared with segmentation algorithm, and it has strong target characterization ability and can be applied to ship targets of different scales.

Mechatronics is a synthesis of mechanical engineering and electronic engineering, and computer engineering, distinct areas that overlap in the design of systems. It represents the interdisciplinary nature of design and development of today's products.;The current research focuses on the design, construction and testing of a computer controlled autonomous model car which can exhibit intelligent behavior such as timed course execution, obstacle detection, and response to sensor inputs. The car is intended as a mechatronics design project that will be integrated into an existing one-semester mechanical engineering undergraduate instrumentation course.;The car was designed around a microprocessor board (Tern Analog Drive) controlled by a 16-bit microcontroller (Tern V104) and equipped with several sensor channels. Two stepper motors were used to propel and guide the car. Photocells were used to detect the path. The control program was written in Turbo C.;The car was tested on a path of reflective white tape about 2 inches wide. The path consists of a 36-inch straight portion followed by a 17-inch radius of curvature curved portion, and completed by a 6-inch straight section with an obstacle at the end. The autonomous car successfully traversed the path and stopped when it detected the obstacle.;It was concluded that a successful mechatronic design project could be developed around the construction and testing of an autonomous car.

Target detection (TD) is a major task in hyperspectral image (HSI) processing which, due to the high spectral resolution, requires dealing with the curse of dimensionality. The integrated feature extraction and selection is a well-known solution for dimensionality reduction of HSIs. In this study, a new method is presented to improve the performance of TD algorithms based on principal component analysis (PCA) feature space. In this method, using the implantation of the target spectrum (TS) in the HSI and following the simulated targets in the PCA feature space, the best principal components (PCs) are selected. Then, using the mixing and unmixing coefficients of the PCs, a new TS and a new image in the PCA feature space are created. Afterwards, using the new spectrum of the target, the TD algorithm is run on the new HSI. The performance of the proposed method is compared to nine counterpart algorithms on Hymap and Hyperion HSI. All the comparisons are performed using adaptive coherence estimator (ACE) TD algorithm. Experimental results illustrate that the proposed method, compared to its counterparts, yields superior performance based on the false alarm rate (FAR) measure. It gives an average FAR value of about 16, which is approximately 9% better than that of its best counterparts.

In most hyperspectral target detection applications, targets are usually small and require both spatial as well as spectral detection. Hyperspectral imaging facilitates target detection (TD) applications greatly, however, due to large spectral content, hyperspectral data requires dimensionality reduction (DR) which also leads to loss of target information both at full pixel and subpixel level. Literature reports many DR and TD algorithms in practice. Several studies have focussed on assessing the loss of target information in DR, however, not much work seems to have been done to assess loss of target information in full pixel and subpixel TD in hyperspectral data with and without DR. This paper seeks to study various combinations of DR techniques combined with full pixel and subpixel TD algorithms. The results indicate that in the case of full pixel targets, both DR and TD contribute to the loss of target information, however, there is more loss of target information in the case when DR precedes TD in comparison to a case where TD is applied without DR. In the case of subpixel TD, however, there appears to be loss of subpixel target information in the case where TD alone is performed in comparison to a case where DR precedes TD.

Vehicle detection is an important technology in au-tonomous driving, for which high detection accuracy and real-time performance are often required. The YOLOv5-GE vehicle detection algorithm is proposed to address the situation that the YOLOv5 vehicle detection model has false detection and missed detection for small and dense targets in complex environments. The global attention mechanism is added to the backbone net-work of the YOLOOv5 model, which is composed of two inde-pendent submodules of channel attention and convolutional spa-tial attention, which prevents the loss of information to a certain extent and amplifies the interaction of global dimensions. Second-ly, the training process is optimized using the Focal-EloU loss function to replace the GloU loss function, which improves the accuracy of vehicle detection. Finally, the proposed YOLOv5-GE algorithm and the YOLOv5 algorithm are subjected to a con-trolled experiment on the KITTI dataset. The experimental re-sults show that the YOLOv5-GE algorithm achieves an average accuracy of 86% while maintaining real-time performance, which is 2.5% higher than that of the YOLOv5 algorithm, and can im-prove the detection accuracy of small and dense targets in com-plex environments.

Object detection is a well-known task in the field of computer vision, especially the small target detection problem that has aroused great academic attention. In order to improve the detection performance of small objects, in this article, a novel enhanced multiscale feature fusion method is proposed, namely, the atrous spatial pyramid pooling-balanced-feature pyramid network (ABFPN). In particular, the atrous convolution operators with different dilation rates are employed to make full use of context information, where the skip connection is applied to achieve sufficient feature fusions. In addition, there is a balanced module to integrate and enhance features at different levels. The performance of the proposed ABFPN is evaluated on three public benchmark datasets, and experimental results demonstrate that it is a reliable and efficient feature fusion method. Furthermore, in order to validate the applicational potential in small objects, the developed ABFPN is utilized to detect surface tiny defects of the printed circuit board (PCB), which acts as the neck part of an improved PCB defect detection (IPDD) framework. While designing the IPDD, several powerful strategies are also employed to further improve the overall performance, which is evaluated via extensive ablation studies. Experiments on a public PCB defect detection database have demonstrated the superiority of the designed IPDD framework against the other seven state-of-the-art methods, which further validates the practicality of the proposed ABFPN.