Hybrid Point Cloud Semantic Compression for Automotive Sensors: A Performance Evaluation

Varischio, Andrea; Mandruzzato, Francesco; Bullo, Marcello; Giordani, Marco; Testolina, Paolo; Zorzi, Michele

doi:10.1109/icc42927.2021.9500523

Cited by 13 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, 2D compression and, in particular, PNG and J-LS, outperforms the Octree-based compression. In fact, unlike their 2D counterparts, Octree methods tend to overfit the data and cannot detect and appropriately remove redundant information hidden in the point cloud representations [9], resulting in a dramatic drop in the compression rate when increasing the resolution. On the contrary, PNG still guarantees a promising 80% compression rate, up to 25% better than Octree.…”

Section: B Numerical Resultsmentioning

confidence: 99%

“…4 (below) illustrates that image-based methods are still faster than the 3D ones. Notably, decompression takes less time than compression, a critical feature for autonomous driving since decompression is generally executed on-board of cars [9].…”

Section: B Numerical Resultsmentioning

confidence: 99%

“…However, this typically requires machine learning methods to be trained and validated for identifying the critical data, which may be difficult to do on board of vehicles [8]. In any case, data rates could be further reduced if the LiDAR point clouds were efficiently compressed before data are validated and broadcast [9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Point Cloud Compression for Efficient Data Broadcasting: A Performance Comparison

Nardo¹,

Peressoni²,

Testolina³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The worldwide commercialization of fifth generation (5G) wireless networks and the exciting possibilities offered by connected and autonomous vehicles (CAVs) are pushing toward the deployment of heterogeneous sensors for tracking dynamic objects in the automotive environment. Among them, Light Detection and Ranging (LiDAR) sensors are witnessing a surge in popularity as their application to vehicular networks seem particularly promising. LiDARs can indeed produce a threedimensional (3D) mapping of the surrounding environment, which can be used for object detection, recognition, and topography. These data are encoded as a point cloud which, when transmitted, may pose significant challenges to the communication systems as it can easily congest the wireless channel. Along these lines, this paper investigates how to compress point clouds in a fast and efficient way. Both 2D-and a 3D-oriented approaches are considered, and the performance of the corresponding techniques is analyzed in terms of (de)compression time, efficiency, and quality of the decompressed frame compared to the original. We demonstrate that, thanks to the matrix form in which LiDAR frames are saved, compression methods that are typically applied for 2D images give equivalent results, if not better, than those specifically designed for 3D point clouds.

show abstract

Section: B Numerical Resultsmentioning

confidence: 99%

Section: B Numerical Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Point Cloud Compression for Efficient Data Broadcasting: A Performance Comparison

Nardo¹,

Peressoni²,

Testolina³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work we consider the sensor data from the Kitti multimodal dataset, collected using a Volkswagen Passat equipped with a Velodyne LiDAR [8]. In particular, we rely on the data compression pipeline proposed in [28]. First, we infer semantic segmentation of point clouds with RangeNet++ [20].…”

Section: Application Modelmentioning

confidence: 99%

“…• The Quality of Experience (QoE): The transmitted data should be accurate enough to perform driving operations. For our case study, the Quality of Experience (QoE) depends on the symmetric point-to-point Chamfer Distance CD sym , which is inversely proportional to the quality of the received data [28]. To incorporate both these factors, the agent reward is designed to balance between QoS and QoE via a tuning parameter 𝛼 ∈ [0, 1].…”

Section: Ai Algorithmmentioning

confidence: 99%

Artificial Intelligence in Vehicular Wireless Networks: A Case Study Using ns-3

Drago¹,

Zugno²,

Mason³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) techniques have emerged as a powerful approach to make wireless networks more efficient and adaptable. In this paper we present an ns-3 simulation framework, able to implement AI algorithms for the optimization of wireless networks. Our pipeline consists of: (i) a new geometry-based mobility-dependent channel model for V2X; (ii) all the layers of a 5G-NR-compliant protocol stack, based on the ns3-mmwave module; (iii) a new application to simulate V2X data transmission, and (iv) a new intelligent entity for the control of the network via AI. Thanks to its flexible and modular design, researchers can use this tool to implement, train, and evaluate their own algorithms in a realistic and controlled environment. We test the behavior of our framework in a Predictive Quality of Service (PQoS) scenario, where AI functionalities are implemented using Reinforcement Learning (RL), and demonstrate that it promotes better network optimization compared to baseline solutions that do not implement AI.

show abstract

Semantic Segmentation of In-Vehicle Point Cloud With Improved RangeNet++ Loss Function

et al. 2023

View full text Add to dashboard Cite

To solve the problem of inaccurate object segmentation caused by unbalanced samples for in-vehicle point cloud, an improved semantic segmentation network RangeNet++ based on asymmetric loss function (AsL-RangeNet++) is proposed, which uses asymmetric loss (AsL) function and Adam optimizer to calculate and adjust object weights, achieve optimal point cloud segmentation. AsL-RangeNet++ can solve the problem of unbalance between positive and negative samples and label error in multi-label classification by calculating the weights of positive and negative samples respectively and more accurately segments the point cloud of small targets. A large number of experiments on the widely used SemanticKITTI dataset show that the proposed method has higher segmentation accuracy and better adaptability than the current mainstream methods.INDEX TERMS Semantic segmentation, rangenet++, asymmetric loss function, in-vehicle point cloud.

show abstract

Hybrid Point Cloud Semantic Compression for Automotive Sensors: A Performance Evaluation

Cited by 13 publications

References 21 publications

Point Cloud Compression for Efficient Data Broadcasting: A Performance Comparison

Point Cloud Compression for Efficient Data Broadcasting: A Performance Comparison

Artificial Intelligence in Vehicular Wireless Networks: A Case Study Using ns-3

Semantic Segmentation of In-Vehicle Point Cloud With Improved RangeNet++ Loss Function

Contact Info

Product

Resources

About