Related papers: Accurate Bounding-box Regression with Distance-IoU…

Vision-based estimation of the motion of a moving target is usually formulated as a bearing-only estimation problem where the visual measurement is modeled as a bearing vector. Although the bearing-only approach has been studied for…

Multi-Object Tracking (MOT) aims to detect and associate all targets of given classes across frames. Current dominant solutions, e.g. ByteTrack and StrongSORT++, follow the hybrid pipeline, which first accomplish most of the associations in…

Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. Our study reveals that the primary reason lies in two aspects: (1) The limited center-offset prediction seriously impairs the…

In the field of state-of-the-art object detection, the task of object localization is typically accomplished through a dedicated subnet that emphasizes bounding box regression. This subnet traditionally predicts the object's position by…

In object detection, determining which anchors to assign as positive or negative samples, known as anchor assignment, has been revealed as a core procedure that can significantly affect a model's performance. In this paper we propose a…

In Few-Shot Object Detection (FSOD), detecting small objects is extremely difficult. The limited supervision cripples the localization capabilities of the models and a few pixels shift can dramatically reduce the Intersection over Union…

Single-stage object detectors have been widely applied in computer vision applications due to their high efficiency. However, we find that the loss functions adopted by single-stage object detectors hurt the localization accuracy seriously.…

Estimating the target extent poses a fundamental challenge in visual object tracking. Typically, trackers are box-centric and fully rely on a bounding box to define the target in the scene. In practice, objects often have complex shapes and…

Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more complicated…

For the training of face detection network based on R-CNN framework, anchors are assigned to be positive samples if intersection-over-unions (IoUs) with ground-truth are higher than the first threshold(such as 0.7); and to be negative…

This paper presents Ego-Centric Intersection-over-Union (EC-IoU), addressing the limitation of the standard IoU measure in characterizing safety-related performance for object detectors in navigating contexts. Concretely, we propose a…

Existing visual tracking methods usually localize a target object with a bounding box, in which the performance of the foreground object trackers or detectors is often affected by the inclusion of background clutter. To handle this problem,…

When tracking maneuvering targets, model-driven approaches encounter difficulties in comprehensively delineating complex real-world scenarios and are prone to model mismatch when the targets maneuver. Meanwhile, contemporary data-driven…

Multiple object tracking (MOT) depends heavily on selection of true positive detected bounding boxes. However, this aspect of the problem is mostly overlooked or mitigated by employing two-stage association and utilizing low confidence…

In recent years, anchor-free object detection models combined with matching algorithms are used to achieve real-time muti-object tracking and also ensure high tracking accuracy. However, there are still great challenges in multi-object…

3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection…

Visual Inertial Odometry (VIO) is one of the most established state estimation methods for mobile platforms. However, when visual tracking fails, VIO algorithms quickly diverge due to rapid error accumulation during inertial data…

Road object detection is an important branch of automatic driving technology, The model with higher detection accuracy is more conducive to the safe driving of vehicles. In road object detection, the omission of small objects and occluded…

The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current…

The critical challenge in tracking-by-detection framework is how to avoid drift problem during online learning, where the robust features for a variety of appearance changes are difficult to be learned and a reasonable intersection over…