[CVPR'23 WAD] Keynote - Hang Zhao, Tsinghua University

Talk given at the CVPR Workshop on Autonomous Driving 2023: cvpr2023.wad.vision/.
00:00 Introduction
00:27 A Simplified Self-Driving Stack
01:05 ViP3D: End-to-End Visual Prediction
02:25 Scalability
04:56 3D Occupancy Prediction
07:28 Auto-Labeling Occupancy Datasets
12:25 The Occ3D and SSCBench Benchmarks
13:47 Handling New Geo-Locations
16:31 VectorMapNet
18:59 Neural Map Priors
22:10 Map Prior Improving Range and Robustness
23:35 Conclusion

[@pervezbhan1708]

3D representations can provide valuable information for self-driving systems, but they are typically used in conjunction with other sensor modalities and data sources to create a comprehensive understanding of the environment. While 3D representations, such as point clouds or voxel grids, can capture geometric details of the surroundings, they have certain limitations that make additional information necessary. Here are a few reasons why 3D representations alone may not be sufficient for self-driving: Limited Field of View: 3D representations typically rely on sensors like lidar to capture the surrounding environment. However, lidar sensors have a limited field of view and can struggle with detecting objects beyond their range or behind obstacles. Therefore, additional sensor modalities like cameras and radar are used to provide complementary information. Perception Challenges: Understanding the environment goes beyond geometry. Perception tasks like object detection, classification, and semantic segmentation require information beyond 3D representations. Cameras, for example, provide valuable color and texture information that aids in object recognition and scene understanding. Dynamic Objects: Self-driving systems need to account for the motion and behavior of dynamic objects like pedestrians, cyclists, and other vehicles. 3D representations alone may not capture the temporal aspect of these objects. Additional information, such as object tracking and prediction algorithms, are necessary to anticipate and plan for the future movements of these dynamic entities. Environmental Context: Environmental context, such as traffic signs, road markings, and traffic signals, plays a critical role in self-driving. While some aspects of this information can be captured in 3D representations, other details may require explicit detection and recognition algorithms designed for specific objects or structures. To build robust and reliable self-driving systems, it's common to integrate data from various sensors, including cameras, lidars, radars, and other sources, to create a holistic understanding of the environment. Combining multiple sensor modalities and data sources allows for redundancy, robustness in different environmental conditions, and a richer representation of the surroundings. User 3D occupancy prediction ChatGPT 3D occupancy prediction is a technique used in self-driving and robotics to estimate the occupancy or occupancy probability of the environment in three-dimensional space. It involves predicting which regions of the 3D space are occupied by obstacles or objects and which regions are free or unoccupied. This information is crucial for path planning, obstacle avoidance, and collision prevention. There are various approaches and algorithms used for 3D occupancy prediction, and here are a few common techniques: Voxel Grids: Voxel grids are a popular representation for 3D occupancy prediction. The 3D space is discretized into small volumetric cells called voxels. Each voxel can be marked as occupied, free, or unknown based on sensor measurements. Algorithms like occupancy grid mapping or probabilistic occupancy mapping can update and maintain the occupancy probabilities of the voxels over time. Point Cloud Processing: Point clouds obtained from lidar sensors are often used for 3D occupancy prediction. Various techniques, such as point cloud segmentation, clustering, and surface reconstruction, can be applied to identify and estimate the occupancy of objects in the point cloud data. Deep Learning: Deep learning methods, particularly convolutional neural networks (CNNs) and their variants, can be employed for 3D occupancy prediction. These networks can learn to directly predict occupancy probabilities or voxel-wise occupancy labels from 3D input data, such as point clouds or voxel grids. Training these models requires labeled data that indicates the occupancy status of each voxel or point. Sensor Fusion: 3D occupancy prediction can also benefit from sensor fusion, where data from multiple sensors, such as lidar, cameras, and radars, are combined to create a more comprehensive representation. Sensor fusion techniques, like Kalman filters or particle filters, can be used to integrate the data from different sensors and refine the occupancy predictions. The accuracy and reliability of 3D occupancy prediction depend on factors such as sensor quality, sensor placement, calibration, and the algorithms used. It's common to combine 3D occupancy prediction with other perception tasks, such as object detection and semantic segmentation, to create a more detailed understanding of the environment for autonomous systems.

[@nonietoomila8890]

0:47 🎉🎉😅😅😅😢😢😮😮😮😮😢😢😂😂😂😂😂❤❤❤❤❤🎉🎉🎉❤❤❤❤❤❤❤