Related papers: Tracking objects using 3D object proposals

Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image. Nonetheless, region proposal algorithms are known to be the bottleneck in most…

A robust 3D object tracker which continuously tracks surrounding objects and estimates their trajectories is key for self-driving vehicles. Most existing tracking methods employ a tracking-by-detection strategy, which usually requires…

Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object poses to reconstruct dynamic objects in canonical space and…

We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects using a monocular RGB camera. The key idea is to derive a region-based cost function using temporally consistent local color histograms. While such region-based…

Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for…

We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local…

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region…

We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate…

Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…

Recent learning methods for object pose estimation require resource-intensive training for each individual object instance or category, hampering their scalability in real applications when confronted with previously unseen objects. In this…

Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes…

Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections…

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In…

Deploying autonomous robots in crowded indoor environments usually requires them to have accurate dynamic obstacle perception. Although plenty of previous works in the autonomous driving field have investigated the 3D object detection…

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the…

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction…

Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…

This paper explores the use of applying a deep learning approach for 3D object detection to compute the relative position of an Unmanned Aerial Vehicle (UAV) from an Unmanned Ground Vehicle (UGV) equipped with a LiDAR sensor in a GPS-denied…

Object pose estimation underwater allows an autonomous system to perform tracking and intervention tasks. Nonetheless, underwater target pose estimation is remarkably challenging due to, among many factors, limited visibility, light…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…