paper-with-me

Papers

Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving

2020-11-27 · Zhenxun Yuan, Xiao Song, Lei Bai, Wengang Zhou, Zhe Wang, Wanli Ouyang

The strong demand of autonomous driving in the industry has lead to strong interest in 3D object detection and resulted in many excellent 3D object detection algorithms. However, the vast majority of algorithms only model single-frame data, ignoring the temporal information of the sequence of data. In this work, we propose a new transformer, called Temporal-Channel Transformer, to model the spatial-temporal domain and channel domain relationships for video object detecting from Lidar data. As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i.e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner. Specifically, the temporal-channel encoder of the transformer is designed to encode the information of different channels and frames by utilizing the correlation among features from different channels and frames. On the other hand, the spatial decoder of the transformer will decode the information for each location of the current frame. Before conducting the object detection with detection head, the gate mechanism is deployed for re-calibrating the features of current frame, which filters out the object irrelevant information by repetitively refine the representation of target frame along with the up-sampling process. Experimental results show that we achieve the state-of-the-art performance in grid voxel-based 3D object detection on the nuScenes benchmark.

📄 PDF Abstract BibTeX arXiv:2011.13628

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionAutonomous DrivingDecoderObjectobject-detectionObject DetectionVideo Object Detection

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention

2020-04-03 · CVPR 2020 6 · Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou 외

Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D vid…

Objectobject-detectionObject DetectionVideo Object Detection

Multi-modal Sensor Registration for Vehicle Perception via Deep Neural Networks

2014-12-22 · Michael Giering, Vivek Venugopalan, Kishore Reddy

The ability to simultaneously leverage multiple modes of sensor information is critical for perception of an automated vehicle's physical surroundings. Spatio-temporal alignment of registration of the incoming informatio…

Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding

2026-02-02 · Soheil Behnam Roudsari, Alexandre S. Brandão, Felipe N. Martins arxiv

Indoor service robots need perception that is robust, more privacy-friendly than RGB video, and feasible on embedded hardware. We present a camera-free 2D LiDAR object detection pipeline that encodes short-term temporal …

Object Detection

Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds

2022-07-26 · Junbo Yin, Jianbing Shen, Xin Gao, David Crandall 외

Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., the point cloud vi…

3D Object DetectionGraph Neural Networkobject-detectionObject Detection+1

Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models

2026-08-26 · Jihun Kim, Hyun-Kurl Jang, Hyemin Yang, Jinnyeong Yang 외 arxiv

Progress in 4D LiDAR segmentation is bottlenecked by data. Assigning temporally consistent labels across sparse point cloud sequences is costly and hard to scale, and every new task or domain tends to demand fresh dense …

Scene UnderstandingVideo Segmentation