Lidar Sensor-Based Object Recognition Using Machine Learning

Wang, Rui; An, Mengyu; Shao, Sihan; Yu, Ming‐Whei; Wang, Shifeng; Xu, Xiping

doi:10.1007/s10946-021-09986-x

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object detection in this type of image is difficult because it first requires a denoising operation, followed by the complexity of extracting features, considering the lack of explicit, neighboring information. Several traditional image processing techniques can be applied, such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Multilayer Perceptron, Logistic Regression, and a revised version of the Histogram of Oriented Gradient technique, called 3DHOG [ 23 , 24 ]. Deep-learning-based techniques have also been presented in the literature, where some approaches may include an automatic search for patterns of interest in the point cloud or the use of R-CNNs for proposing three-dimensional regions of interest [ 25 , 26 ].…”

Section: Object Detection State-of-the-artmentioning

confidence: 99%

Design and Characterization of a Powered Wheelchair Autonomous Guidance System

Gallo,

Shallari,

Carratù

et al. 2024

Sensors

View full text Add to dashboard Cite

The current technological revolution driven by advances in machine learning has motivated a wide range of applications aiming to improve our quality of life. Representative of such applications are autonomous and semiautonomous Powered Wheelchairs (PWs), where the focus is on providing a degree of autonomy to the wheelchair user as a matter of guidance and interaction with the environment. Based on these perspectives, the focus of the current research has been on the design of lightweight systems that provide the necessary accuracy in the navigation system while enabling an embedded implementation. This motivated us to develop a real-time measurement methodology that relies on a monocular RGB camera to detect the caregiver’s feet based on a deep learning method, followed by the distance measurement of the caregiver from the PW. An important contribution of this article is the metrological characterization of the proposed methodology in comparison with measurements made with dedicated depth cameras. Our results show that despite shifting from 3D imaging to 2D imaging, we can still obtain comparable metrological performances in distance estimation as compared with Light Detection and Ranging (LiDAR) or even improved compared with stereo cameras. In particular, we obtained comparable instrument classes with LiDAR and stereo cameras, with measurement uncertainties within a magnitude of 10 cm. This is further complemented by the significant reduction in data volume and object detection complexity, thus facilitating its deployment, primarily due to the reduced complexity of initial calibration, positioning, and deployment compared with three-dimensional segmentation algorithms.

show abstract