KPRNet: Improving projection-based LiDAR semantic segmentation (original) (raw)
Related papers
RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Perception in autonomous vehicles is often carried out through a suite of different sensing modalities. Given the massive amount of openly available labeled RGB data and the advent of high-quality deep learning algorithms for image-based recognition, high-level semantic perception tasks are predominantly solved using high-resolution cameras. As a result of that, other sensor modalities potentially useful for this task are often ignored. In this paper, we push the state of the art in LiDAR-only semantic segmentation forward in order to provide another independent source of semantic information to the vehicle. Our approach can accurately perform full semantic segmentation of LiDAR point clouds at sensor frame rate. We exploit range images as an intermediate representation in combination with a Convolutional Neural Network (CNN) exploiting the rotating LiDAR sensor model. To obtain accurate results, we propose a novel postprocessing algorithm that deals with problems arising from this intermediate representation such as discretization errors and blurry CNN outputs. We implemented and thoroughly evaluated our approach including several comparisons to the state of the art. Our experiments show that our approach outperforms state-of-the-art approaches, while still running online on a single embedded GPU. The code can be accessed at https://github.com/PRBonn/lidar-bonnetal.
SalsaNext: Fast Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
ArXiv, 2020
In this paper, we introduce SalsaNext for the semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we have an additional layer in the encoder and decoder, introduce the context module, switch from stride convolution to average pooling and also apply central dropout treatment. To directly optimize the Jaccard index, we further combine the weighted cross entropy loss with Lovász-Softmax loss [2]. We provide a thorough quantitative evaluation on the Semantic-KITTI dataset [3], which demonstrates that the proposed SalsaNext outperforms other state-of-the-art semantic segmentation networks in terms of accuracy and computation time. We also release our source code https://github.com/TiagoCortinhal/SalsaNext.
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019
We propose LU-Net-for LiDAR U-Net, a new method for the semantic segmentation of a 3D LiDAR point cloud. Instead of applying some global 3D segmentation method such as PointNet, we propose an end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem. We first extract high-level 3D features for each point given its 3D neighbors. Then, these features are projected into a 2D multichannel range-image by considering the topology of the sensor. Thanks to these learned features and this projection, we can finally perform the segmentation using a simple U-Net segmentation network, which performs very well while being very efficient. In this way, we can exploit both the 3D nature of the data and the specificity of the Li-DAR sensor. This approach outperforms the state-of-the-art by a large margin on the KITTI dataset, as our experiments show. Moreover, this approach operates at 24fps on a single GPU. This is above the acquisition rate of common LiDAR sensors which makes it suitable for real-time applications.
RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud
2019
This paper proposes RIU-Net (for Range-Image U-Net), the adaptation of a popular semantic segmentation network for the semantic segmentation of a 3D LiDAR point cloud. The point cloud is turned into a 2D range-image by exploiting the topology of the sensor. This image is then used as input to a U-net. This architecture has already proved its efficiency for the task of semantic segmentation of medical images. We demonstrate how it can also be used for the accurate semantic segmentation of a 3D LiDAR point cloud and how it represents a valid bridge between image processing and 3D point cloud processing. Our model is trained on range-images built from KITTI 3D object detection dataset. Experiments show that RIU-Net, despite being very simple, offers results that are comparable to the state-of-the-art of range-image based methods. Finally, we demonstrate that this architecture is able to operate at 90fps on a single GPU, which enables deployment for real-time segmentation.
Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Semantic segmentation of 3D point cloud data is essential for enhanced high-level perception in autonomous platforms. Furthermore, given the increasing deployment of LiDAR sensors onboard of cars and drones, a special emphasis is also placed on non-computationally intensive algorithms that operate on mobile GPUs. Previous efficient state-of-the-art methods relied on 2D spherical projection of point clouds as input for 2D fully convolutional neural networks to balance the accuracy-speed trade-off. This paper introduces a novel approach for 3D point cloud semantic segmentation that exploits multiple projections of the point cloud to mitigate the loss of information inherent in single projection methods. Our Multi-Projection Fusion (MPF) framework analyzes spherical and bird's-eye view projections using two separate highly-efficient 2D fully convolutional models then combines the segmentation results of both views. The proposed framework is validated on the SemanticKITTI dataset where it achieved a mIoU of 55.5 which is higher than state-of-the-art projection-based methods RangeNet++ [23] and PolarNet [44] while being 1.6x faster than the former and 3.1x faster than the latter.
IEEE Access
In the autonomous car, perception with point cloud semantic segmentation helps obtain a wealth of information about the surrounding road environment. Despite the massive progress of recent researches, the existing machine learning networks are still insufficient for online applications of autonomous driving due to too subdivided classes, the lack of training data, and their heavy computing load. To solve these problems, we propose a fast and lite point cloud semantic segmentation network for autonomous driving, which utilizes LiDAR synthetic data to improve the performance by transfer learning. First, we modify the labeling classes and generate the LiDAR synthetic data-set for additional training to alleviate the lack of training data of the realistic data-set. Then, to lower the computing load, we adopt a projection-based method and apply a lightweight segmentation network to projected LiDAR images, which has drastically reduced computing. Finally, we verified and evaluated the proposed network in this paper through experiments. Experimental results show that the proposed network can perform the three-dimensional point cloud semantic segmentation in an online way, in which the inference speed overwhelms the existing algorithms. INDEX TERMS Autonomous driving, point cloud semantic segmentation, synthetic dataset, computing load reduction.
In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch from stride convolution to average pooling and also apply central dropout treatment. To directly optimize the Jaccard index, we further combine the weighted cross entropy loss with Lovász-Softmax loss [2]. We finally inject a Bayesian treatment to compute the epistemic and aleatoric uncertainties for each point in the cloud. We provide a thorough quantitative evaluation on the Semantic-KITTI dataset [3], which demonstrates that the proposed SalsaNext outperforms other state-of-the-art semantic segmentation networks and ranks first on the Semantic-KITTI leaderboard. We also release our source code https://github.com/TiagoCortinhal/SalsaNext.
SHREC 2020: 3D point cloud semantic segmentation for street scenes
Computers & Graphics, 2020
Scene understanding of large-scale 3D point clouds of an outer space is still a challenging task. Compared with simulated 3D point clouds, the raw data from LiDAR scanners consist of tremendous points returned from all possible reflective objects and they are usually non-uniformly distributed. Therefore, its costeffective to develop a solution for learning from raw large-scale 3D point clouds. In this track, we provide large-scale 3D point clouds of street scenes for the semantic segmentation task. The data set consists of 80 samples with 60 for training and 20 for testing. Each sample with over 2 million points represents a street scene and includes a couple of objects. There are five meaningful classes: building, car, ground, pole and vegetation. We aim at localizing and segmenting semantic objects from these large-scale 3D point clouds. Four groups contributed their results with different methods. The results show that learningbased methods are the trend and one of them achieves the best performance on both Overall Accuracy and mean Intersection over Union. Next to the learning-based methods, the combination of hand-crafted detectors are also reliable and rank second among comparison algorithms.
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are either in relative small spatial scales or have limited semantic annotations due to the expensive cost of data acquisition and data annotation, which severely limits the development of fine-grained semantic understanding in the context of 3D point clouds. In this paper, we present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is five times the number of labeled points than the existing largest point cloud dataset. Our dataset consists of large areas from two UK cities, covering about 6 km 2 of the city landscape. In the dataset, each 3D point is labeled as one of 13 semantic classes. We extensively evaluate the performance of state-of-the-art algorithms on our dataset and provide a comprehensive analysis of the results. In particular, we identify several key challenges towards urban-scale point cloud understanding. The dataset is available at https: //github.com/QingyongHu/SensatUrban.
SalsaNext: Fast, Uncertainty-Aware Semantic Segmentation of LiDAR Point Clouds
2020
In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch from stride convolution to average pooling and also apply central dropout treatment. To directly optimize the Jaccard index, we further combine the weighted cross-entropy loss with Lovasz-Softmax loss [2]. We finally inject a Bayesian treatment to compute the epistemic and aleatoric uncertainties for each point in the cloud. We provide a thorough quantitative evaluation on the Semantic-KITTI dat...