The performance of object detection models for autonomous driving is increasingly advancing. However, to recognize static traffic targets such as traffic light recognition and traffic sign recognition, the detectable ...
详细信息
ISBN:
(数字)9788993215380
ISBN:
(纸本)9798331517939
The performance of object detection models for autonomous driving is increasingly advancing. However, to recognize static traffic targets such as traffic light recognition and traffic sign recognition, the detectable distance in images plays a crucial role in the planning strategies and performance of recognition algorithms for autonomous driving systems. This study analyzes the detection performance and detection range of traffic lights by a monocular camera on an autonomous driving vehicle. The detection model used is the YOLOv7-x model, with the original images segmented to 1x, 1/2x, and 1/3x of the model input size. The distances are obtained through high-precision maps and vehicle-mounted GPS/RTK. The results of this study indicate the scalability of the detection distance of a monocular camera’s object detection in an autonomous driving environment using a single model. It further demonstrates a proportional relationship between the detection distance and the model input size. It confirms the scalability of detection distances with cameras of different fields of view using a single model.
The GNSS signal used for vehicle localization exhibits a shaded area such as a tunnel. To accurately estimate the location in the shaded area, the accumulated position error must be compensated with information obtain...
详细信息
In urban cities, with increasing acceptability of shared spaces used by pedestrians and personal mobility devices (PMDs), there is need for pragmatic socially acceptable path planning and navigation management policie...
详细信息
In this paper are presented simple and practical solutions to extrinsic calibration between a camera and a 2D laser sensor, without overlap. Previous methods utilized a plane or an intersecting line of two planes as a...
详细信息
In this paper are presented simple and practical solutions to extrinsic calibration between a camera and a 2D laser sensor, without overlap. Previous methods utilized a plane or an intersecting line of two planes as a geometric constraint with enough common field-of-view. These required additional sensors to calibrate non-overlapping systems. In this paper, we present two methods for solving the problem - one utilizes a plane; the other utilizes an intersecting line of two planes. For each method, an initial solution of the relative positions of a non-overlapping camera and a laser sensor, was computed by adopting a reasonable assumption about geometric structures. Then we refined it via non-linear optimization, even if the assumption was not perfectly satisfied. Both simulation results and experiments using real data showed that the proposed methods provided reliable results compared to ground-truth, and similar or better results than those provided by a conventional method.
Building maps of unknown environments is a critical factor for autonomous navigation and homing, and this problem is especially challenging in large-scale environments. Recently, sensor fusion systems such as combinat...
详细信息
ISBN:
(纸本)9781467317375
Building maps of unknown environments is a critical factor for autonomous navigation and homing, and this problem is especially challenging in large-scale environments. Recently, sensor fusion systems such as combinations of cameras and laser sensors have become popular in the effort to ensure a general level of performance in this task. In this paper, we present a new homing method in a large-scale environment using a laser-camera fusion system. Instead of fusing data to form a single map builder, we adaptively select sensor data to handle environments which contain ambiguity. For autonomous homing, we propose a new mapping strategy for building a hybrid map and a return strategy for selecting the next target waypoints efficiently. The experimental results demonstrate that the proposed algorithm enables the autonomous homing of a robot in a large-scale indoor environments in real time.
暂无评论