Segmentation and Unsupervised Part-based Discovery of Repetitive Objects

Triebel, Rudolph; Shin, Jiwon; Siegwart, R.

doi:10.15607/rss.2010.vi.009

Cited by 51 publications

(41 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D voxels can be also created to reduce computational costs by grouping sets of neighbor points. Graphs can be later built on top of grouped voxels to classify them in objects [30,25,19]. More recent methods are able to process the point cloud space (raw, or reduced in voxels) to extract hand-crafted features such as spin images, shape models or geometric statistics [3].…”

Section: Related Workmentioning

confidence: 99%

Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications

Pino

Vaquero

Masini

et al. 2017

ROBOT 2017: Third Iberian Robotics Conference

View full text Add to dashboard Cite

Abstract. Vehicle detection and tracking in real scenarios are key components to develop assisted and autonomous driving systems. Lidar sensors are specially suitable for this task, as they bring robustness to harsh weather conditions while providing accurate spatial information. However, the resolution provided by point cloud data is very scarce in comparison to camera images. In this work we explore the possibilities of Deep Learning (DL) methodologies applied to low resolution 3D lidar sensors such as the Velodyne VLP-16 (PUCK), in the context of vehicle detection and tracking. For this purpose we developed a lidar-based system that uses a Convolutional Neural Network (CNN), to perform pointwise vehicle detection using PUCK data, and Multi-Hypothesis Extended Kalman Filters (MH-EKF), to estimate the actual position and velocities of the detected vehicles. Comparative studies between the proposed lower resolution (VLP-16) tracking system and a high-end system, using Velodyne HDL-64, were carried out on the Kitti Tracking Benchmark dataset. Moreover, to analyze the influence of the CNN-based vehicle detection approach, comparisons were also performed with respect to the geometric-only detector. The results demonstrate that the proposed low resolution Deep Learning architecture is able to successfully accomplish the vehicle detection task, outperforming the geometric baseline approach. Moreover, it has been observed that our system achieves a similar tracking performance to the high-end HDL-64 sensor at close range. On the other hand, at long range, detection is limited to half the distance of the higher-end sensor.

show abstract

Section: Related Workmentioning

confidence: 99%

Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications

Pino

Vaquero

Masini

et al. 2017

ROBOT 2017: Third Iberian Robotics Conference

View full text Add to dashboard Cite

show abstract

“…Triebel et al [9] modified the FH algorithm for range images to propose an unsupervised probabilistic segmentation technique. In this approach, the 3D data is first over-segmented during pre-processing.…”

Section: Graph Clusteringmentioning

confidence: 99%

Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation

2013

View full text Add to dashboard Cite

Segmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classify urban scenes based on a super-voxel segmentation of sparse 3D data obtained from LiDAR sensors is presented. The 3D point cloud is first segmented into voxels, which are then characterized by several attributes transforming them into super-voxels. These are joined together by using a link-chain method rather than the usual region growing algorithm to create objects. These objects are then classified using geometrical models and local descriptors. In order to evaluate the results, a new metric that combines both segmentation and classification results simultaneously is presented. The effects of voxel size and incorporation of RGB color and laser reflectance intensity on the classification results are also discussed. The method is evaluated on standard data sets using different metrics to demonstrate its efficacy.

show abstract

“…They examine range differences in consecutive laser scan points to get an approximate estimate if a point is lying on a horizontal or on a vertical surface. Triebel et al use Conditional Random Fields to segment and discover repetitive objects in 3D laser range scans [11]. Rusu et al extract hybrid representations of objects consisting of detected shapes, as well as surface reconstructions where no shapes have been detected [9].…”

Section: Related Workmentioning

confidence: 99%

Real-Time Plane Segmentation Using RGB-D Cameras

Holz

Hölzer

Rusu

et al. 2012

Lecture Notes in Computer Science

215

155

View full text Add to dashboard Cite

Abstract. Real-time 3D perception of the surrounding environment is a crucial precondition for the reliable and safe application of mobile service robots in domestic environments. Using a RGB-D camera, we present a system for acquiring and processing 3D (semantic) information at frame rates of up to 30Hz that allows a mobile robot to reliably detect obstacles and segment graspable objects and supporting surfaces as well as the overall scene geometry. Using integral images, we compute local surface normals. The points are then clustered, segmented, and classified in both normal space and spherical coordinates. The system is tested in different setups in a real household environment. The results show that the system is capable of reliably detecting obstacles at high frame rates, even in case of obstacles that move fast or do not considerably stick out of the ground. The segmentation of all planes in the 3D data even allows for correcting characteristic measurement errors and for reconstructing the original scene geometry in far ranges.

show abstract

Segmentation and Unsupervised Part-based Discovery of Repetitive Objects

Cited by 51 publications

References 17 publications

Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications

Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications

Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation

Real-Time Plane Segmentation Using RGB-D Cameras

Contact Info

Product

Resources

About