Point Cloud Compression: Impact on Object Detection in Outdoor Contexts.

Increasing demand for more reliable and safe autonomous driving means that data involved in the various aspects of perception, such as object detection, will become more granular as the number and resolution of sensors progress. Using these data for on-the-fly object detection causes problems related to the computational complexity of onboard processing in autonomous vehicles, leading to a desire to offload computation to roadside infrastructure using vehicle-to-infrastructure communication links. The need to transmit sensor data also arises in the context of vehicle fleets exchanging sensor data, over vehicle-to-vehicle communication links. Some types of sensor data modalities, such as Light Detection and Ranging (LiDAR) point clouds, are so voluminous that their transmission is impractical without data compression. With most emerging autonomous driving implementations being anchored on point cloud data, we propose to evaluate the impact of point cloud compression on object detection. To that end, two different object detection architectures are evaluated using point clouds from the KITTI object dataset: raw point clouds and point clouds compressed with a state-of-the-art encoder and three different compression levels. The analysis is extended to the impact of compression on depth maps generated from images projected from the point clouds, with two conversion methods tested. Results show that low-to-medium levels of compression do not have a major impact on object detection performance, especially for larger objects. Results also show that the impact of point cloud compression is lower when detecting objects using depth maps, placing this particular method of point cloud data representation on a competitive footing compared to raw point cloud data.

Colored Point Cloud Registration by Depth Filtering.

In the last stage of colored point cloud registration, depth measurement errors hinder the achievement of accurate and visually plausible alignments. Recently, an algorithm has been proposed to extend the Iterative Closest Point (ICP) algorithm to refine the measured depth values instead of the pose between point clouds. However, the algorithm suffers from numerical instability, so a postprocessing step is needed to restrict erroneous output depth values. In this paper, we present a new algorithm with improved numerical stability. Unlike the previous algorithm heavily relying on point-to-plane distances, our algorithm constructs a cost function based on an adaptive combination of two different projected distances to prevent numerical instability. We address the problem of registering a source point cloud to the union of the source and reference point clouds. This extension allows all source points to be processed in a unified filtering framework, irrespective of the existence of their corresponding points in the reference point cloud. The extension also improves the numerical stability of using the point-to-plane distances. The experiments show that the proposed algorithm improves the registration accuracy and provides high-quality alignments of colored point clouds.

High-Fidelity Depth Upsampling Using the Self-Learning Framework.

This paper presents a depth upsampling method that produces a high-fidelity dense depth map using a high-resolution RGB image and LiDAR sensor data. Our proposed method explicitly handles depth outliers and computes a depth upsampling with confidence information. Our key idea is the self-learning framework, which automatically learns to estimate the reliability of the upsampled depth map without human-labeled annotation. Thereby, our proposed method can produce a clear and high-fidelity dense depth map that preserves the shape of object structures well, which can be favored by subsequent algorithms for follow-up tasks. We qualitatively and quantitatively evaluate our proposed method by comparing other competing methods on the well-known Middlebury 2014 and KITTIbenchmark datasets. We demonstrate that our method generates accurate depth maps with smaller errors favorable against other methods while preserving a larger number of valid points, as we also show that our approach can be seamlessly applied to improve the quality of depth maps from other depth generation algorithms such as stereo matching and further discuss potential applications and limitations. Compared to previous work, our proposed method has similar depth errors on average, while retaining at least 3% more valid depth points.