SECOND: Sparsely Embedded Convolutional Detection
LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. Voxel-based 3D convolutional networks have been used for some time to enhance the retention of information when processing point cloud LiDAR data. However, problems remain, including a slow inference speed and low orientation estimation performance. We therefore investigate an improved sparse convolution method for such networks, which significantly increases the speed of both training and inference. We also introduce a new form of angle loss regression to improve the orientation estimation performance and a new data augmentation approach that can enhance the convergence speed and performance. The proposed network produces state-of-the-art results on the KITTI 3D object detection benchmarks while maintaining a fast inference speed.
Code (1)
Tasks
3D Object DetectionAutonomous DrivingData Augmentationobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL
When producing a model to object detection in a specific context, the first obstacle is to have a dataset labeling the desired classes. In RoboCup, some leagues already have more than one dataset to train and evaluate a …
BenchmarkingObjectobject-detectionObject Detection+1Trainable Projected Gradient Detector for Sparsely Spread Code Division Multiple Access
Sparsely spread code division multiple access (SCDMA) is a promising non-orthogonal multiple access technique for future wireless communications. In this paper, we propose a novel trainable multiuser detector called spar…
LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems
Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory than image classification. Thus the cons…
Face Detectionimage-classificationImage ClassificationObject+3MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
Monocular 3D object detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely anno…
Monocular 3D Object DetectionTiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful tec…
Objectobject-detectionObject DetectionObject Localization+1