Instant Object Detection in Lidar Point Clouds

Abstract

Abstract-In this paper 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. Firstly, 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 (CNN). Finally we refine the classification with contextual features considering the possible expected scene topologies. We tested our algorithm in real Lidar measurements, containing 1159 objects captured from different urban scenarios.

Street object classification via LIDARs with only a single or a few layers

“…In We present a comparison (Table VII) with state of the art 3D recognition method as well. The test dataset is presented in [4], it contains segmented objects. Intensity data is not provided, so it was left out from our descriptor.…”

“…Results show that our method perform better in case of almost every measure. Vehicle category is an exception, however, authors of [4] execute a contextual refinement for this class. [4] Categories Precision (%) Recall (%) F-rate [4] proposed [4] proposed [4] proposed 5 shows examples of categorized plane curves.…”

“…Methods working on 3D LIDARs have the potential for the classification of several object classes, because these methods have more information than in the case of dealing with separated 2D LIDAR segments. Works like [4] and [5] use 2D or 3D Convolutional networks for classification, but they require point clouds as input. Compared to this, in work of [1] a solution was proposed for the problem, where 2.5D point clouds are not available, only partial (but connected) object data.…”

“…Dealing with LIDARs with many planes (e.g. Velodyne HDL-64 4 ), we will experience that far objects will be represented in only a few planes and they cannot be treated as point clouds (Figure 1). In [1], the authors proposed a solution for the relatively slow Automated Guided Vehicles, where a 3D reconstruction was made by fusing the separated planes.…”

3D CNN-Based Semantic Labeling Approach for Mobile Laser Scanning Data

“…Several techniques extract various object blob candidates by geometric scene segmentation [2], [13], then the blobs are classified using shape descriptors, or deep neural networks [13]. Although this process can be notably fast, the main bottleneck of the approach is that it largely depends on the quality of the object detection step.…”