Attila Börcs

Extraction of Vehicle Groups in Airborne Lidar Point Clouds With Two-Level Point Processes

In this paper, we present a new object-based hierarchical model for the joint probabilistic extraction of vehicles and groups of corresponding vehicles-called traffic segments-in airborne light detection and ranging (Lidar) point clouds collected from dense urban areas. First, the 3-D point set is classified into terrain, vehicle, roof, vegetation, and clutter classes. Then, the points with the corresponding class labels and echo strength (i.e., intensity) values are projected to the ground. In the obtained 2-D class and intensity maps, we approximate the top view projections of vehicles by rectangles. Since our tasks are simultaneously the extraction of the rectangle population which describes the position, size, and orientation of the vehicles and grouping the vehicles into the traffic segments, we propose a hierarchical two-level marked point process (MPP) (L2MPP) model for the problem. The output vehicle and traffic segment configurations are extracted by an iterative stochastic optimization algorithm. We have tested the proposed method with real data of a discrete-return Lidar sensor providing up to four range measurements for each laser pulse. Using manually annotated ground-truth information on a data set containing 1009 vehicles, we provide quantitative evaluation results showing that the L2MPP model surpasses two earlier grid-based approaches, a 3-D point-cloud-based process and a single-layer MPP solution. The accuracy of the proposed method measured in F-rate is 97% at object level, 83% at pixel level, and 95% at group level.

Fast 3-D Urban Object Detection on Streaming Point Clouds

Efficient and fast object detection from continuously streamed 3-D point clouds has a major impact in many related research tasks, such as autonomous driving, self localization and mapping and understanding large scale environment. This paper presents a LIDAR-based framework, which provides fast detection of 3-D urban objects from point cloud sequences of a Velodyne HDL-64E terrestrial LIDAR scanner installed on a moving platform. The pipeline of our framework receives raw streams of 3-D data, and produces distinct groups of points which belong to different urban objects. In the proposed framework we present a simple, yet efficient hierarchical grid data structure and corresponding algorithms that significantly improve the processing speed of the object detection task. Furthermore, we show that this approach confidently handles streaming data, and provides a speedup of two orders of magnitude, with increased detection accuracy compared to a baseline connected component analysis algorithm.

Object extraction in urban environments from large-scale dynamic point cloud datasets

In this paper, we introduce a system framework which can automatically interpret large point cloud datasets collected from dense urban areas by moving aerial or terrestrial Lidar platforms. We propose novel algorithms for region segmentation, motion analysis, object identification and population level scene analysis which steps can highly contribute to organize the data into a semantically indexed structure, enabling quick responses for content based user queries about the environment. The system is tested on real Lidar data, and for demonstration quantitative evaluation is given on vehicle detection.

Instant Object Detection in Lidar Point Clouds

In this letter, we present a new approach for object classification in continuously streamed Lidar point clouds collected from urban areas. The input of our framework is raw 3-D point cloud sequences captured by a Velodyne HDL-64 Lidar, and we aim to extract all vehicles and pedestrians in the neighborhood of the moving sensor. We propose a complete pipeline developed especially for distinguishing outdoor 3-D urban objects. First, we segment the point cloud into regions of ground, short objects (i.e., low foreground), and tall objects (high foreground). Then, using our novel two-layer grid structure, we perform efficient connected component analysis on the foreground regions, for producing distinct groups of points, which represent different urban objects. Next, we create depth images from the object candidates, and apply an appearance-based preliminary classification by a convolutional neural network. Finally, we refine the classification with contextual features considering the possible expected scene topologies. We tested our algorithm in real Lidar measurements, containing 1485 objects captured from different urban scenarios.

A Model-based Approach for Fast Vehicle Detection in Continuously Streamed Urban LIDAR Point Clouds

Detection of vehicles in crowded 3-D urban scenes is a challenging problem in many computer vision related research fields, such as robot perception, autonomous driving, self-localization, and mapping. In this paper we present a model-based approach to solve the recognition problem from 3-D range data. In particular, we aim to detect and recognize vehicles from continuously streamed LIDAR point cloud sequences of a rotating multi-beam laser scanner. The end-to-end pipeline of our framework working on the raw streams of 3-D urban laser data consists of three steps (1) producing distinct groups of points which represent different urban objects (2) extracting reliable 3-D shape descriptors specifically designed for vehicles, considering the need for fast processing speed (3) executing binary classification on the extracted descriptors in order to perform vehicle detection. The extraction of our efficient shape descriptors provides a significant speedup with and increased detection accuracy compared to a PCA based 3-D bounding box fitting method used as baseline.

Dynamic 3D Environment Perception and Reconstruction Using a Mobile Rotating Multi-beam Lidar Scanner

In this chapter we introduce cooperating techniques for environment perception and reconstruction based on dynamic point cloud sequences of a single rotating multi-beam (RMB) Lidar sensor, which monitors the scene either from a moving vehicle top or from a static installed position. The joint aim of the addressed methods is to create 4D spatio-temporal models of large dynamic urban scenes containing various moving and static objects. Standalone RMB Lidar devices have been frequently applied in robot navigation tasks and proved to be efficient in moving object detection and recognition. However, they have not been widely exploited yet in video surveillance or dynamic virtual city modeling. We address here three different application areas of RMB Lidar measurements, starting from people activity analysis, through real time object perception for autonomous driving, until dynamic scene interpretation and visualization. First we introduce a multiple pedestrian tracking system with short term and long term person assignment steps. Second we present a model based real-time vehicle recognition approach. Third we propose techniques for geometric approximation of ground surfaces and building facades using the observed point cloud streams. This approach extracts simultaneously the reconstructed surfaces, motion information and objects from the registered dense point cloud completed with point time stamp information.