Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

by   Qi Chen, et al.

Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities. Existing methods strive to organize the points regularly, e.g. voxelize, pass them through a designed 2D/3D neural network, and then define object-level anchors that predict offsets of 3D bounding boxes using collective evidence from all the points on the objects of interest. Converse to the state-of-the-art anchor-based methods, based on the very same nature of data sparsity and irregularities, we observe that even points on an isolated object part are informative about position and orientation of the object. We thus argue in this paper for an approach opposite to existing methods using object-level anchors. Technically, we propose to represent an object as a collection of point cliques; one can intuitively think of these point cliques as hotspots, giving rise to the representation of Object as Hotspots (OHS). Based on OHS, we propose a Hotspot Network (HotSpotNet) that performs 3D object detection via firing of hotspots without setting the predefined bounding boxes. A distinctive feature of HotSpotNet is that it makes predictions directly from individual hotspots, and final results are obtained by aggregating these hotspot predictions. Experiments on the KITTI benchmark show the efficacy of our proposed OHS representation. Our one-stage, anchor-free HotSpotNet beats all other one-stage detectors by at least 2 cars , cyclists and pedestrian for all difficulty levels. Notably, our proposed method performs better on small and difficult objects and we rank the first among all the submitted methods on pedestrian of KITTI test set.


page 14

page 15


CenterNet3D:An Anchor free Object Detector for Autonomous Driving

Accurate and fast 3D object detection from point clouds is a key task in...

MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds

Recent works in object detection in LiDAR point clouds mostly focus on p...

CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point Cloud

At present, the anchor-based or anchor-free models that use LiDAR point ...

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Recently, promising applications in robotics and augmented reality have ...

Multimodal Transformer for Automatic 3D Annotation and Object Detection

Despite a growing number of datasets being collected for training 3D obj...

ImpDet: Exploring Implicit Fields for 3D Object Detection

Conventional 3D object detection approaches concentrate on bounding boxe...

ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera

People detection in top-view, fish-eye images is challenging as people i...

Please sign up or login with your details

Forgot password? Click here to reset