Related papers: Subpixel-Precise Tracking of Rigid Objects in Real…
Visual object tracking, which is primarily based on visible light image sequences, encounters numerous challenges in complicated scenarios, such as low light conditions, high dynamic ranges, and background clutter. To address these…
In this paper, we present a multi-object 6D detection and tracking pipeline for potentially similar and non-textured objects. The combination of a convolutional neural network for object classification and rough pose estimation with a local…
The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such…
Real-time tracking of previously unseen, highly dynamic objects in contact-rich scenes, such as during dexterous in-hand manipulation, remains a major challenge. Pure vision-based approaches often fail under heavy occlusions due to frequent…
Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data…
Variations of target appearance such as deformations, illumination variance, occlusion, etc., are the major challenges of visual object tracking that negatively impact the performance of a tracker. An effective method to tackle these…
Online multi-object tracking (MOT) is extremely important for high-level spatial reasoning and path planning for autonomous and highly-automated vehicles. In this paper, we present a modular framework for tracking multiple objects…
Rotation estimation of known rigid objects is important for robotic applications such as dexterous manipulation. Most existing methods for rotation estimation use intermediate representations such as templates, global or local feature…
Existing shape estimation methods for deformable object manipulation suffer from the drawbacks of being off-line, model dependent, noise-sensitive or occlusion-sensitive, and thus are not appropriate for manipulation tasks requiring high…
We propose the task Future Object Detection, in which the goal is to predict the bounding boxes for all visible objects in a future video frame. While this task involves recognizing temporal and kinematic patterns, in addition to the…
We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment. Specifically, we construct a 'coreset' representation of streaming data using a…
Obstacle Detection is a central problem for any robotic system, and critical for autonomous systems that travel at high speeds in unpredictable environment. This is often achieved through scene depth estimation, by various means. When fast…
In this paper we present a new approach for efficient regression based object tracking which we refer to as Deep- LK. Our approach is closely related to the Generic Object Tracking Using Regression Networks (GOTURN) framework of Held et al.…
Object tracking is divided into single-object tracking (SOT) and multi-object tracking (MOT). MOT aims to maintain the identities of multiple objects across a series of continuous video sequences. In recent years, MOT has made rapid…
We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered…
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture…
360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception. In this paper, we explore 360{\deg} images for visual object tracking and perceive new challenges caused by large…
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…
Physics-based understanding of object interactions from sensory observations is an essential capability in augmented reality and robotics. It enables to capture the properties of a scene for simulation and control. In this paper, we propose…
Accurate people counting in smart buildings and intelligent transportation systems is crucial for energy management, safety protocols, and resource allocation. This is especially critical during emergencies, where precise occupant counts…