Related papers: DeepScale: Online Frame Size Adaptation for Multi-…
The goal of multi-object tracking is to detect and track all objects in a scene while maintaining unique identifiers for each, by associating their bounding boxes across video frames. This association relies on matching motion and…
Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…
The automatization of Multi-Object Tracking becomes a demanding task in real unconstrained scenarios, where the algorithms have to deal with crowds, crossing people, occlusions, disappearances and the presence of visually similar…
Running deep learning models on resource-constrained edge devices has drawn significant attention due to its fast response, privacy preservation, and robust operation regardless of Internet connectivity. While these devices already cope…
Determining the drivable area, or free space segmentation, is critical for mobile robots to navigate indoor environments safely. However, the lack of coherent markings and structures (e.g., lanes, curbs, etc.) in indoor spaces places the…
High frame rate and accurate depth estimation plays an important role in several tasks crucial to robotics and automotive perception. To date, this can be achieved through ToF and LiDAR devices for indoor and outdoor applications,…
Visual tracking is a fundamental problem in computer vision. Recently, some deep-learning-based tracking algorithms have been achieving record-breaking performances. However, due to the high complexity of deep learning, most deep trackers…
In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…
Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…
We present a method to perform online Multiple Object Tracking (MOT) of known object categories in monocular video data. Current Tracking-by-Detection MOT approaches build on top of 2D bounding box detections. In contrast, we exploit…
Achieving both efficiency and strong discriminative ability in lightweight visual tracking is a challenge, especially on mobile and edge devices with limited computational resources. Conventional lightweight trackers often struggle with…
Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…
In this paper, we propose the first higher frame rate video dataset (called Need for Speed - NfS) and benchmark for visual object tracking. The dataset consists of 100 videos (380K frames) captured with now commonly available higher frame…
Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements…
Multiple Object Tracking (MOT) is an important task in computer vision. MOT is still challenging due to the occlusion problem, especially in dense scenes. Following the tracking-by-detection framework, we propose the Box-Plane Matching…
In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less…
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot…
Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…
Unpredictable movement patterns and small visual mark make precise tracking of fast-moving tiny objects like a racquetball one of the challenging problems in computer vision. This challenge is particularly relevant for sport robotics…
This paper presents a fast and modular framework for Multi-Object Tracking (MOT) based on the Markov descision process (MDP) tracking-by-detection paradigm. It is designed to allow its various functional components to be replaced by…