Free Space Detection Algorithm Using Object Tracking for Autonomous Vehicles

Lee, Yeongwon; You, Byungyong

doi:10.3390/s22010315

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the process of constructing 3D occupancy grid map, ray casting algorithm is introduced to determine the coordinates of different state grids [11] . Based on the current position of the autonomous vehicle and the obstacle surface position returned by the laser point cloud, the algorithm trawls the grid traversed by the beam to obtain the coordinates of each grid.…”

Section: Ray Casting Algorithmmentioning

confidence: 99%

A 3D map construction method for autonomous vehicles in unknown environment

Peng,

Chunning

2024

Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023)

View full text Add to dashboard Cite

Environment map construction is one of the key research directions of autonomous driving technology. Autonomous vehicle driving in unknown environments need to detect obstacles and identify passable areas. Traditional methods usually use two-dimensional planar maps without vertical information, and cannot exclude the influence of dynamic obstacles. In order to reflect the unknown environment information more accurately, this paper proposes a 3D map construction method based on Apollo autonomous driving system. Firstly, the point cloud data and pose data were obtained by the sensors mounted on the vehicle. Secondly, the 3D environment space was divided into different grids by the occupancy grid map algorithm. Then, the coordinates of different state grids are updated by ray casting algorithm. Finally, the Point Pillar algorithm is used to identify the dynamic obstacles and eliminate the residual shadows to obtain a more accurate 3D map. The experimental results show that the proposed method can effectively construct the unknown environment map, accurately reflect the three-dimensional information in the environment, and avoid the influence of dynamic obstacles.

show abstract

Section: Ray Casting Algorithmmentioning

confidence: 99%

A 3D map construction method for autonomous vehicles in unknown environment

Peng,

Chunning

2024

Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023)

View full text Add to dashboard Cite

show abstract

“…Real-time object trackers are used in various sectors, including smart surveillance [1], robotics [2], medical imaging [3], autonomous vehicle [4], sports analysis support system [5], and augmented reality [6]. The actuator within an object tracker responds dynamically to feedback from object recognition algorithms that operate remotely in the cloud [7].…”

Section: Introductionmentioning

confidence: 99%

Trackez: An IoT-Based 3D-Object Tracking From 2D Pixel Matrix Using Mez and FSL Algorithm

et al. 2023

View full text Add to dashboard Cite

The imaging devices sense light reflected from objects and reconstruct images using the 2D-sensor matrix. It is a 2D Cartesian coordinate system where the depth dimension is absent. The absence of a depth axis on 2D images imposes challenges in locating and tracking objects in a 3D environment. Real-time object tracking faces another challenge imposed by network latency. This paper presents the development and analysis of a real-time, real-world object tracker called Trackez, which is capable of tracking within the top hemisphere. It uses Machine Vision at the IoT Edge (Mez) technology to mitigate latency sensitivity. A novel algorithm, Follow-Satisfy-Loop (FSL), has been developed and implemented in this paper that optimally tracks the target. It does not require the depth-axis. The simple and innovative design and incorporation of Mez technology have made the proposed object tracker a latency-insensitive, Z-axis-independent, and effective system. The Trackez reduces the average latency by 85.08% and improves the average accuracy by 81.71%. The object tracker accurately tracks objects moving in regular and irregular patterns at up to 5.4ft/s speed. This accurate, latency tolerant, and Z-axis independent tracking system contributes to developing a better robotics system that requires object tracking.

show abstract

“…Using these static data, the ground and obstacles are recognized, and the free space is marked in a simplified polygonal form. Y. Lee et al [4] consider free space detection in dynamic environments. By reflecting the velocity data of obstacles, they are able to classify an area in which driving is possible or not.…”

Section: Introductionmentioning

confidence: 99%

Safety Prompt Advanced Driver-Assistance System with Lane-Change Prediction and Free Space Detection

Zhao

Wang

Xiong

et al. 2022

2022 IEEE 17th International Conference on Control &Amp; Automation (ICCA)

View full text Add to dashboard Cite

With the map navigation system achieving the positioning accuracy at the lane level, the lane level navigation system began to be applied in digital navigation software. The new generation of navigation system allows human drivers to accurately identify road conditions without road experience. However, in actual use, drivers still need to complete lanechanging behavior independently. The navigation system does not provide relevant real-time traffic flow information and safety prediction. Therefore, this paper innovatively combines the free space detection and lane change prediction algorithm in actual driving, and puts forward this Safety Prompt Advanced Driver-Assistance System (SPADAS). It can predict the lanechange decision and lane-change trajectory around in a short period of time in the future according to the current state and historical trajectory of the surrounding vehicles, and combine these prediction information to provide the driver or the path planning module of the self-driving vehicle with the predicted free space in the near future. The free space provided by this Advanced Driver-Assistance System (ADAS) includes three types: continuing driving according to the current state or changing lanes to the left or right. At the same time, it also provides the required recommended driving trajectory. The evaluation test of this ADAS has been done through a simulation testbed of the NGSIM dataset built with Eclipse SUMO.

show abstract

Free Space Detection Algorithm Using Object Tracking for Autonomous Vehicles

Cited by 5 publications

References 30 publications

A 3D map construction method for autonomous vehicles in unknown environment

A 3D map construction method for autonomous vehicles in unknown environment

Trackez: An IoT-Based 3D-Object Tracking From 2D Pixel Matrix Using Mez and FSL Algorithm

Safety Prompt Advanced Driver-Assistance System with Lane-Change Prediction and Free Space Detection

Contact Info

Product

Resources

About