Related papers: Focal and Efficient IOU Loss for Accurate Bounding…
Detecting rotated objects accurately and efficiently is a significant challenge in computer vision, particularly in applications such as aerial imagery, remote sensing, and autonomous driving. Although traditional object detection…
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to…
We present an endpoint box regression module(epBRM), which is designed for predicting precise 3D bounding boxes using raw LiDAR 3D point clouds. The proposed epBRM is built with sequence of small networks and is computationally lightweight.…
Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary…
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.…
Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual…
Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased…
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection…
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…
Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In…
In this paper, we introduce an innovative method to improve the convergence speed and accuracy of object detection neural networks. Our approach, CONVERGE-FAST-AUXNET, is based on employing multiple, dependent loss metrics and weighting…
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. In this work, by intensive diagnosis experiments, we quantify…
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…
Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks. We investigate the relationship between bounding box localization errors and human task performance. We use…
We propose a Ground IoU (Gr-IoU) to address the data association problem in multi-object tracking. When tracking objects detected by a camera, it often occurs that the same object is assigned different IDs in consecutive frames, especially…
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…
Object segmentation plays an important role in the modern medical image analysis, which benefits clinical study, disease diagnosis, and surgery planning. Given the various modalities of medical images, the automated or semi-automated…
Recently Deep Learning based Siamese Networks with region proposals for visual object tracking becoming more popular. These networks, while testing, perform extra computations on output if trained network, to predict the bounding box. This…
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment…
Object detection in aerial images is a challenging task due to the lack of visible features and variant orientation of objects. Significant progress has been made recently for predicting targets from aerial images with horizontal bounding…