Related papers: Closely-Spaced Object Classification Using MuyGPyS
While building up a catalog of Earth orbiting objects, if the available optical observations are sparse, not deliberate follow ups of specific objects, no orbit determination is possible without previous correlation of observations obtained…
Field robotics in perceptually-challenging environments require fast and accurate state estimation, but modern LiDAR sensors quickly overwhelm current odometry algorithms. To this end, this paper presents a lightweight frontend LiDAR…
In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including position,…
Dramatic appearance variation due to pose constitutes a great challenge in fine-grained recognition, one which recent methods using attention mechanisms or second-order statistics fail to adequately address. Modern CNNs typically lack an…
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples. The mechanism of the human visual system is to interpret spatial relationships…
While existing semi-supervised object detection (SSOD) methods perform well in general scenes, they encounter challenges in handling oriented objects in aerial images. We experimentally find three gaps between general and oriented object…
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts or keypoints [11, 21]. In this paper we build on a recent…
Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods. However, due to uncontrollable object poses in images, distinctive details carried…
Simultaneous object recognition and pose estimation are two key functionalities for robots to safely interact with humans as well as environments. Although both object recognition and pose estimation use visual input, most state-of-the-art…
Nowadays robots play an increasingly important role in our daily life. In human-centered environments, robots often encounter piles of objects, packed items, or isolated objects. Therefore, a robot must be able to grasp and manipulate…
In existing works that learn representation for object detection, the relationship between a candidate window and the ground truth bounding box of an object is simplified by thresholding their overlap. This paper shows information loss in…
Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a…
Achieving a balance between computational efficiency and detection accuracy in the realm of rotated bounding box object detection within aerial imagery is a significant challenge. While prior research has aimed at creating lightweight…
Remote sensing object detection is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced…
Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point…
Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…
Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…
Unmanned surface vehicles (USVs) and boats are increasingly important in maritime operations, yet their deployment is limited due to costly sensors and complexity. LiDAR, radar, and depth cameras are either costly, yield sparse point clouds…
Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection performance by leveraging a large number of unlabeled images alongside a…