Related papers: Motion-to-Matching: A Mixed Paradigm for 3D Single…
Category-specific models are provenly valuable methods in 3D single object tracking (SOT) regardless of Siamese or motion-centric paradigms. However, such over-specialized model designs incur redundant parameters, thus limiting the broader…
Multi-object tracking is a cornerstone capability of any robotic system. The quality of tracking is largely dependent on the quality of the detector used. In many applications, such as autonomous vehicles, it is preferable to over-detect…
Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring…
Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions,…
3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature…
Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most…
Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding…
Classical autonomous driving systems connect perception and prediction modules via hand-crafted bounding-box interfaces, limiting information flow and propagating errors to downstream tasks. Recent research aims to develop end-to-end models…
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitable changing of detection scores leads to object missing after…
Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving. Previous works studied each perception task separately, and lacked a collective quantitative…
Recent 3D multi-object tracking (3D MOT) methods mainly follow tracking-by-detection pipelines, but often suffer from high false positives, missed detections, and identity switches, especially in crowded and small-object scenarios. To…
Point cloud 3D object detection has recently received major attention and becomes an active research topic in 3D computer vision community. However, recognizing 3D objects in LiDAR (Light Detection and Ranging) is still a challenge due to…
Although there is a significant development in 3D Multi-view Multi-person Tracking (3D MM-Tracking), current 3D MM-Tracking frameworks are designed separately for footprint and pose tracking. Specifically, frameworks designed for footprint…
Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously…
Multiple Object Tracking (MOT) is an important task in computer vision. MOT is still challenging due to the occlusion problem, especially in dense scenes. Following the tracking-by-detection framework, we propose the Box-Plane Matching…
LIDAR 3D object detection is one of the important tasks for autonomous vehicles. Ensuring that this task operates in real-time is crucial. Toward this, model quantization can be used to accelerate the runtime. However, directly applying…
Visual Object Tracking (VOT) aims to estimate the positions of target objects in a video sequence, which is an important vision task with various real-world applications. Depending on whether the initial states of target objects are…
Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to…
3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To…
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…