Accuracy Of Obstacle Detection Research Articles

Low-altitude UAV obstacle detection method based on position constraint and attention

UAVs are widely used in low-altitude fields for tasks such as power inspection, search and rescue, and reconnaissance. Pre-detection of obstacles during flight is a safety guarantee for completing the given tasks. In order to meet the requirements of obstacle detection accuracy and position regression accuracy when UAVs are flying at low altitudes, a low-altitude UAV obstacle detection method based on position constraint and attention improvement is proposed. Firstly, the shortcomings of the position regression loss function are analyzed, and based on this, a loss function of separating scale loss and integrating direction constraint is proposed to optimize the regression process; secondly, the attention mechanism CBAM is improved, and a dual attention mechanism is proposed to strengthen the feature suppression interference and improve the detection performance. The experimental results show that the improved algorithm has improved mAP 2.28%and mAP@0.5:0.95 2.7%, and has shown better low-altitude obstacle detection performance in both detection accuracy and position regression accuracy.

Calibration and validation of a multi-beam LiDAR onboard China Chang’e lunar probe for landing obstacle avoidance

For automatic exploration of specific areas with high scientific value on the moon and other planets, high-precision obstacle detection and hazard avoidance capabilities are required. Three-dimensional (3D) LiDAR can obtain a high-resolution 3D point cloud, offering significant advantages in landing obstacle avoidance. During the landing of the Chang’e lander, a laser 3D imaging sensor (L3DIS) is used to measure and generate accurate topographic maps of the candidate landing area in real-time to help find a safe landing zone. The L3DIS employs 16 beamlets split from a Gaussian laser beam and 16 channels of linear-array avalanche photodiodes within the same optical path and scans the object with a two-axis galvanometer in a field of view of 29°×33°. The calibration of the systematic errors and the performance of obstacle detection on this sensor are conducted in this paper. First, the instrument components and main error sources of the sensor are introduced, and the systematic errors are calibrated based on planar targets, indicating that the sensor’s accuracy is greater than 4 cm, and the corresponding obstacle detection accuracy is better than 12 cm. Second, the ground validation of obstacle detection is demonstrated, and the obtained point cloud is compared with that obtained by a terrestrial laser scanner, indicating that the sensor has good performance. Finally, the performance of onboard measurement and obstacle detection is analyzed, showing that the sensor can identify obvious craters and rocks, i.e., nine major craters with a maximum and minimum depth of 1.36 m and 0.16 m, respectively, and major rocks with a maximum and minimum height of 0.1 m and 0.05 m, respectively, and main landing area with slop less than 10° except for the edges of craters and rocks.

Smart Stick Revolutionizes Mobility for the Visually Impaired

Visual impairment significantly hinders daily activities, necessitating innovative solutions. This study develops and tests a smart walking stick using NodeMCU ESP-8266, HCSR-04 ultrasonic sensor, DFPlayer, and GPS, monitored via the Blynk app. Employing a research and development approach, the device demonstrated 100% accuracy in obstacle detection and location tracking, providing real-time feedback through audio notifications and smartphone monitoring. This smart walking stick enhances mobility and safety for visually impaired users, representing a significant advancement in assistive technology. Highlights: Accurate Obstacle Detection: 100% accuracy with HCSR-04 ultrasonic sensor. Real-time Monitoring: GPS tracking via Blynk app. Enhanced Mobility: Increases safety and independence for visually impaired users. Keywords: Visual impairment, Smart walking stick, Ultrasonic sensor, GPS tracking, IoT

Developing an expansion‐based obstacle detection using panoptic segmentation

AbstractSafe Micro Aerial Vehicle (MAV) navigation requires detecting and avoiding obstacles. For safe MAV navigation, expansion‐based algorithms are effective for detecting obstacles. However, accurate and real‐time obstacle detection is a fundamental challenge. Some traditional methods focus on extracting geometric features from images and applying geometric constraints to identify potential obstacles. Others may leverage machine learning algorithms for object detection and classification, using features such as texture, shape, and context to distinguish obstacles from background clutter. The choice of approach depends on factors such as the specific requirements of the application, the complexity of the scene, and the available computational resources. Since obstacles, in reality, take the form of objects (e.g., persons, walls, pillars, trees, automobiles, and other structures), it is preferable to represent them according to human comprehension and as objects. Therefore, the objective of this study is to reflect on the previous research and address the issues mentioned above by extracting objects from the fisheye image using a panoptic deep‐learning network. The extracted object regions are, then, used to identify obstacles with a novel area‐based expansion rate we developed in a previous study. We compared the accuracy of obstacle detection in our proposed method to the existing method when moving forward and to the right; thus, we improved it between 10% and 18%, respectively. In addition, compared with the existing method, and due to replacing a single object with multiple regions, obstacle‐detection runtime for forward and right direction is 15.71 and 25.5 times faster, respectively, and the required match points have decreased by 49% and 55%.

Blockchain-Empowered Edge Intelligence for TACS Obstacle Detection: System Design and Performance Optimization

With the significant advantages of system complexity and operating costs, Train Autonomous Circumambulate System (TACS) is gradually replacing the traditional Communication Based Train Control (CBTC) system as the next-generation train operation control system development direction. As train operation and control become more decentralized and autonomous, real-time and accurate obstacle detection, apart from route-level protection, is quite desirable in TACS. Most of the existing researches about obstacle detection focus on detection algorithm optimization based on the once-deployed lifelong use principle, while model re-optimization based on the actual operating environment under unexpected situations and model sharing among multi-users are largely ignored. In this paper, we design a novel obstacle detection system in TACS based on blockchain-empowered Edge Intelligence (EI). To make full use of the massive raw unannotated data collected online, we first propose an SSL-based TACS obstacle detection model. Considering the resource-hungry model training, we introduce EI into TACS and propose a MARL-based task offloading algorithm for secure and efficient computation offloading coordination. Furthermore, we propose a blockchain-based model sharing scheme to facilitate the multi-model parameter exchange and improve the obstacle detection accuracy. Extensive simulation results show that the designed obstacle detection system can effectively improve the TACS obstacle detection performance.

Research on Obstacle Detection and Avoidance of Autonomous Underwater Vehicle Based on Forward-Looking Sonar.

Due to the complexity of the ocean environment, an autonomous underwater vehicle (AUV) is disturbed by obstacles when performing tasks. Therefore, the research on underwater obstacle detection and avoidance is particularly important. Based on the images collected by a forward-looking sonar on an AUV, this article proposes an obstacle detection and avoidance algorithm. First, a deep learning-based obstacle candidate area detection algorithm is developed. This algorithm uses the You Only Look Once (YOLO) v3 network to determine obstacle candidate areas in a sonar image. Then, in the determined obstacle candidate areas, the obstacle detection algorithm based on the improved threshold segmentation algorithm is used to detect obstacles accurately. Finally, using the obstacle detection results obtained from the sonar images, an obstacle avoidance algorithm based on deep reinforcement learning (DRL) is developed to plan a reasonable obstacle avoidance path of an AUV. Experimental results show that the proposed algorithms improve obstacle detection accuracy and processing speed of sonar images. At the same time, the proposed algorithms ensure AUV navigation safety in a complex obstacle environment.

Obstacle Detection Method of Underground Electric Locomotive Rail Based on Instance Segmentation

Real-time and accurate obstacle detection is a vital technology for electric locomotives, especially as driverless vehicles are introduced. A method of obstacle detection for underground electric locomotive rail based on instance segmentation is developed to solve the problems of misdetection and missing detection, low detection accuracy, and slow detection speed of rail obstacles. The method of locating the track mask, demarcating the effective driving boundary, expanding the track mask, and forming the effective driving area is adopted to verify whether the target is an obstacle based on whether the target is located in the effective driving area, to avoid the problem of misdetection and missing detection of the target obstacle. The YOLACT++ (You Only Look At CoefficienTs) model is improved, and path augmentation and target classification loss function replacement strategies are adopted to enhance the model’s ability to detect target details and increase the accuracy of target segmentation. Compared with traditional image processing, this method can detect both straight rail and turnout. The mean average precision of boundary box mAP0.5(box) and mask mAP0.5(mask) of the improved YOLACT++ model reaches 98.52% and 98.55%, which is higher than that of the YOLACT++ model, and the detection frame rate reaches 21.9 frames per second.

A Safety-Assured Semantic Map for an Unstructured Terrain Environment towards Autonomous Engineering Vehicles

Accurate obstacle detection plays a crucial role in the creation of high-precision maps within unstructured terrain environments, as it supplies vital decision-making information for unmanned engineering vehicles. Existing works primarily focus on the semantic segmentation of terrain environments, overlooking the safety aspect of vehicle driving. This paper presents a hazardous obstacle detection framework in addition to driving safety-assured semantic information in the generated high-precision map of unstructured scenarios. The framework encompasses the following key steps. Firstly, a continuous terrain point cloud model is obtained, and a pre-processing algorithm is designed to filter noise and fill holes in the point cloud dataset. The Sobel-G operator is then utilized to establish a digital gradient model, facilitating the labeling of hazardous obstacles. Secondly, a bidirectional long short-term memory (Bi-LSTM) neural network is trained on obstacle categories. Finally, by considering the geometric driving state of the vehicle, obstacles that pose safety risks to the vehicle are accurately extracted. The proposed algorithm is validated through experiments conducted on existing datasets as well as real, unstructured terrain point clouds reconstructed by drones. The experimental results affirm the accuracy and feasibility of the proposed algorithm for obstacle information extraction in unstructured scenes.

Vehicle detection systems for intelligent driving using deep convolutional neural networks

In the paper, a vision-based vehicle identification system is proposed for autonomous intelligent car driving. The accurate detection of obstacles (vehicles) during intelligent car driving allows avoiding crashes, preventing accidents, saving people’s lives and reducing harm. The vehicle detection system, which uses low-quality images captured by a monocular video camera mounted at the front of the car, is based on convolutional neural networks (CNN). The CNN can extract global features of the images using convolutional layers and achieves more accurate, and faithful contours of vehicles. The CNN structure proposed in the paper provides high-accuracy detection of vehicle images. The experiments that have been performed using GTI dataset demonstrate that the CNN-based vehicle detection system achieves very accurate results and is more robust to different variations of images.

A Novel Method for Obstacle Detection in Front of Vehicles Based on the Local Spatial Features of Point Cloud

Obstacle detection is the primary task of the Advanced Driving Assistance System (ADAS). However, it is very difficult to achieve accurate obstacle detection in complex traffic scenes. To this end, this paper proposes an obstacle detection method based on the local spatial features of point clouds. Firstly, the local spatial point cloud of a superpixel is obtained through stereo matching and the SLIC image segmentation algorithm. Then, the probability of the obstacle in the corresponding area is estimated from the spatial feature information of the local plane normal vector and the superpixel point-cloud height, respectively. Finally, the detection results of the two methods are input into the Bayesian framework in the form of probabilities for the final decision. In order to describe the traffic scene efficiently and accurately, the detection results are further transformed into a multi-layer stixel representation. We carried out experiments on the KITTI dataset and compared several obstacle detection methods. The experimental results indicate that the proposed method has advantages in terms of its Pixel-wise True Positive Rate (PTPR) and Pixel-wise False Positive Rate (PFPR), particularly in complex traffic scenes, such as uneven roads.

Modeling and TOPSIS-GRA Algorithm for Autonomous Driving Decision-Making Under 5G-V2X Infrastructure

This paper is to explore the problems of intelligent connected vehicles (ICVs) autonomous driving decision-making under a 5G-V2X structured road environment. Through literature review and interviews with autonomous driving practitioners, this paper firstly puts forward a logical framework for designing a cerebrum-like autonomous driving system. Secondly, situated on this framework, it builds a hierarchical finite state machine (HFSM) model as well as a TOPSIS-GRA algorithm for making ICV autonomous driving decisions by employing a data fusion approach between the entropy weight method (EWM) and analytic hierarchy process method (AHP) and by employing a model fusion approach between the technique for order preference by similarity to an ideal solution (TOPSIS) and grey relational analysis (GRA). The HFSM model is composed of two layers: the global FSM model and the local FSM model. The decision of the former acts as partial input information of the latter and the result of the latter is sent forward to the local path-planning module, meanwhile pulsating feedback to the former as real-time refresh data. To identify different traffic scenarios in a cerebrum-like way, the global FSM model is designed as 7 driving behavior states and 17 driving characteristic events, and the local FSM model is designed as 16 states and 8 characteristic events. In respect to designing a cerebrum-like algorithm for state transition, this paper firstly fuses AHP weight and EWM weight at their output layer to generate a synthetic weight coefficient for each characteristic event; then, it further fuses TOPSIS method and GRA method at the model building layer to obtain the implementable order of state transition. To verify the feasibility, reliability, and safety of the HFSM model as well as its TOPSIS-GRA state transition algorithm, this paper elaborates on a series of simulative experiments conducted on the PreScan8.50 platform. The results display that the accuracy of obstacle detection gets 98%, lane line prediction is beyond 70 m, the speed of collision avoidance is higher than 45 km/h, the distance of collision avoidance is less than 5 m, path planning time for obstacle avoidance is averagely less than 50 ms, and brake deceleration is controlled under 6 m/s2. These technical indexes support that the driving states set and characteristic events set for the HFSM model as well as its TOPSIS-GRA algorithm may bring about cerebrum-like decision-making effectiveness for ICV autonomous driving under 5G-V2X intelligent road infrastructure.

AIoT-Based Smart Stick for Visually Impaired Person

Visually impaired people are facing difficulties during day-to-day activities in terms of traveling and receiving accurate information from their surroundings. Most of the time, visually impaired persons need to rely on others. Blind people cannot walk without the support of a cane. Artificial intelligence of things (AIoT) is the solution to designing smart devices for the visually impaired. We propose a smart stick that overcomes most of the problems of the visually impaired person. The stick actually helps to detect the obstacles faced in day-to-day life. The visually impaired person can also recognize objects and currency with the help of a deep learning algorithm applied to images captured by the camera installed in the stick. The pulse sensor installed on the stick monitors the health of the user. The smart stick is embedded with Raspberry pi and a global positioning system (GPS) that helps in sensing emergency alerts. The proposed smart stick also provides timing information about available buses near the location to enable choosing travel times in advance. Sensors are used for achieving these functions. Android application that is connected with firebase is also developed for tracking data about the user (health, location, etc.) from a remote location. The Overall obstacle detection accuracy of the system is 91.7% for various demonstrations and the single module will be available at around <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\$ $ </tex-math></inline-formula> 50– <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\$ $ </tex-math></inline-formula> 60. The proposed system is cost-effective, lightweight and user-friendly. The main goal of this system is to ensure the safety of visually impaired persons and to provide a better life for them.

Overview of deep learning and mobile edge computing in autonomous driving

In recent years, mobile edge computing and deep learning have attracted strong industry attention in the application scenario of autonomous driving. Mobile edge computing reduces the transmission delay of autonomous driving information by offloading computational tasks to edge servers to reduce the network load; deep learning can effectively improve the accuracy of obstacle detection, thereby enhancing the stability and safety of autonomous driving. This paper first introduces the basic concept and reference architecture of MEC and the commonly used model algorithms in deep learning, and then summarizes the applications of MEC and deep learning in autonomous driving from three aspects: target detection, path planning, and collision avoidance, and finally discusses and outlooks the problems and challenges in current research.

MuSLi: A multi sensor LiDAR detection for C-V2X networks

Obstacle detection is a tool adopted in vehicular safety applications, aiming to detect a moving obstacle in an area of interest with the highest accuracy. Different sensors are used for this aim, such as LiDAR devices mounted on board of a vehicle that capture images of the surrounding environment. Extending the number of LiDAR sensors can be useful to improve the obstacle detection accuracy, since multiple images are captured from different distances and directions, and this represents an interesting approach, specially in case of dense networks with cooperative nodes. In this paper we present MuSLi technique, aiming to (i) provide an accurate obstacle detection and (ii) forward alert messages to other cars in the network, in case of correct detection of a pedestrian crossing the street. MuSLi relies on the connected content islands scenario, where each vehicle defined as a content island subscribes to a service in order to receive and share published messages. Specifically, the road safety service allows the detection of an obstacle through multiple LiDAR sensors from neighboring cars. Furthermore, we investigate the fastest transmission mode among those defined in the C-V2X releases to alert the presence of a pedestrian to the other approaching cars. The proposed technique provides the distances by the crossroad in which is better to use V2V, V2I or V2N according to the environment, the scheduling technique and the measured interference.

Design and Implementation of an Intelligent Assistive Cane for Visually Impaired People Based on an Edge-Cloud Collaboration Scheme

Visually impaired people face many inconveniences in daily life, and there are problems such as high prices and single functions in the market of assistance tools for visually impaired people. In this work, we designed and implemented a low-cost intelligent assistance cane, particularly for visually impaired individuals, based on computer vision, sensors, and an edge-cloud collaboration scheme. Obstacle detection, fall detection, and traffic light detection functions have been designed and integrated for the convenience of moving for visually impaired people. We have also designed an image captioning function and object detection function with high-speed processing capability based on an edge-cloud collaboration scheme to improve the user experience. Experiments show that the performance metrics have an aerial obstacle detection accuracy of 92.5%, fall detection accuracy of 90%, and average image retrieval period of 1.124 s. It proves the characteristics of low power consumption, strong real-time performance, adaptability to multiple scenarios, and convenience, which can ensure the safety of visually impaired people when moving and can help them better perceive and understand the surrounding environment.

Fast and accurate obstacle detection of manipulator in complex human–machine interaction workspace

In order to solve the problems of a large amount of calculation, poor real-time performance, and insufficient detection accuracy in an existing robot obstacle detection system, this paper proposes an improved lightweight You Only Look Once Version 3 algorithm for obstacle detection and tracking, by combining the DeepSort algorithm with a three-dimensional model velocity estimation method. First, the depthwise separable convolution and convolution kernel pruning methods are used to lighten the network. Second, to meet the requirement of dynamic obstacle detection, the DeepSort method is used to track dynamic obstacles and estimate their moving speed. Third, a method of bounding-sphere modeling and discrete marking is proposed to simplify the obstacle model. The experimental results show that: the model size is reduced by 92.11%, which suggests that the proposed lightweight detection system is more suitable for industrial applications; the detection speed in the actual scene reaches 118 frames per second and the average detection accuracy is 92.6%, while the multiple objects tracking accuracy and multiple objects tracking precision are all above 0.8 in the dynamic obstacle tracking process. Static and dynamic obstacles in the workspace can be detected simultaneously with an average positioning accuracy error of 1.5 cm. The proposed model can not only effectively improve the detection efficiency of obstacles in the manipulator workspace but also enhance the safety of industrial robot systems.

MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving: A Review

With autonomous driving developing in a booming stage, accurate object detection in complex scenarios attract wide attention to ensure the safety of autonomous driving. Millimeter wave (mmWave) radar and vision fusion is a mainstream solution for accurate obstacle detection. This article presents a detailed survey on mmWave radar and vision fusion based obstacle detection methods. First, we introduce the tasks, evaluation criteria, and datasets of object detection for autonomous driving. The process of mmWave radar and vision fusion is then divided into three parts: sensor deployment, sensor calibration, and sensor fusion, which are reviewed comprehensively. Specifically, we classify the fusion methods into data level, decision level, and feature level fusion methods. In addition, we introduce three-dimensional(3D) object detection, the fusion of lidar and vision in autonomous driving and multimodal information fusion, which are promising for the future. Finally, we summarize this article.

Performance Evaluation of 5G Waveforms for Joint Radar Communication over 77 GHz and 24 GHz ISM Bands

The V2X environment poses many challenges to emerging wireless communication systems, while it is crucial to ensure the efficiency and safety of road users. Requiring continual localization of the surroundings and accurate obstacle detection while providing high reliability in dense networks and low latency in high-mobility environment communication systems imposes a challenge to the driver-assistance field given that we are overly limited in terms of frequency bands and resources. Hence, pooling of the available frequency resources between different applications can help increase the spectral efficiency. A new collaborative approach multiplexed in the time domain, namely RadCom, which can be described as a joint radar and communication system that performs both vehicle-to-everything communication and detection of the neighboring obstacles in the vehicular environment, has been proposed to overcome the limitations of the existing conventional radar system. Based on orthogonal frequency division multiplexing (OFDM), this RadCom system proved to be suitable up to now for V2X. Moreover, a new RadCom system based on universal frequency multi-carrier (UFMC), an advanced fifth-generation (5G) waveform, has been proposed to enhance the spectral efficiency and surmount the shortcomings induced by the OFDM waveform. This recent RadCom system has been studied in the new frequency range of 76–81 GHz; precisely, 77 GHz. Hence, in this paper, we propose to compare both subsystems of the proposed RadCom system over two different frequency carriers, 24 GHz and 77 GHz, and to adopt the proper system parametrization in order to meet appropriate wireless solutions for automotive RadCom systems.

Automatic Obstacle-Crossing Planning for a Transmission Line Inspection Robot Based on Multisensor Fusion

Accurate obstacle detection and proper behavior planning are key factors in the success of transmission line inspection robots. To achieve the autonomous location and identification of line obstacles in the operation of transmission line inspection robots, we propose a method in which information from various sensors is used to control a robot such that it can reliably and stably approach, locate, and identify obstacles. The accuracy and real-time requirements of obstacle information in the autonomous operation of the inspection robot are analyzed, a multi-sensor integrated structure for line obstacle location and identification is proposed, and an obstacle location and identification algorithm is designed for each stage. The principle of monocular vision ranging is used to control the robot such that it approaches obstacles and enters the short-range location stage, where the reliable location of obstacles is achieved via collision-encoder-current sensor data fusion. Obstacles are identified and the identification results are combined with those of the approaching rolling phase. The robot state vector is constructed according to the obstacle detection information and information measured by the robot sensors. Based on the current state vector, combined with the robot obstacle surmounting process, an obstacle surmounting behavior planning method based on multi-sensor fusion is implemented. Experiments were conducted using laboratory-simulated lines to verify the effectiveness of the proposed method for obstacle detection and behavior planning during transmission line inspection.

Blind spot sensor systems for power wheelchairs: obstacle detection accuracy, cognitive task load, and perceived usefulness among older adults

Purpose Blind spot sensor systems can improve power wheelchair (PWC) safety. This research (1) compared accuracy of obstacle detection in the rear of a wheelchair with and without a sensor system, and (2) explored cognitive task load and perceived usability, safety, confidence and awareness in a laboratory setting, and (3) PWC users’ perceptions in real-world settings. Materials and methods A mixed-method design was used. PWC users were provided with the sensor system. In laboratory accuracy of obstacle detection with and without a sensor system, cognitive task load and perceived usability, safety, confidence and awareness were evaluated. Participants then used the sensor system at home for two-months before completing semi-structured interviews. Statistical and thematic analyses were conducted. Results Among 11 PWC users (age = 67.5 ± 7.5y), obstacles were detected more accurately with sensor system than without (p < 0.001). Using the sensor system required lower cognitive task loads (p = 0.005). The system was perceived by most users as easy to use (9/11) and its capabilities meeting their requirements (8/11). Most users did not perceive safety (9/11), confidence (9/11) or increased awareness (10/11) in the laboratory. Three themes emerged in the follow-ups: perceived usefulness, barriers to use, and recommendations. Four participants reported continued use after 2 months, reporting perceived increased awareness, convenience, and independence using the system. Those who discontinued use reported perceived lack of usefulness and technical issues. Recommendations included types of users who can benefit and sensor improvements. Conclusions Sensor systems may improve obstacle detection accuracy while reducing cognitive task load. However, larger scale implementation should consider recommendations for PWC service provision. IMPLICATIONS FOR REHABILITATION Blind spot sensors systems increased speed and accuracy of obstacle detection when using a power wheelchair. Technical and hardware issues encountered by PWC users highlight the need for training and support services. Technical support was out of scope for the current research project and will be explored in future research given the critical role it might play in the usability and adoption of assistive technologies. PWC users perceived there to be practical uses for blind spot sensor systems.