Related papers: Segmentation-Based Bounding Box Generation for Omn…
Vehicle-to-Pedestrian (V2P) communication can significantly improve pedestrian safety at a signalized intersection. It is unlikely that pedestrians will carry a low latency communication enabled device and activate a pedestrian safety…
To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the…
Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are…
Pedestrian detection is one of the most popular topics in computer vision and robotics. Considering challenging issues in multiple pedestrian detection, we present a real-time depth-based template matching people detector. In this paper, we…
Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative…
Pedestrian detection is used in many vision based applications ranging from video surveillance to autonomous driving. Despite achieving high performance, it is still largely unknown how well existing detectors generalize to unseen data.…
Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view (BEV) from multi-view images. In MVPD, end-to-end trainable deep learning methods have progressed greatly. However, they often struggle to…
The design of pedestrian detectors seldom considers the unique characteristics of this task and usually follows the common strategies for general object detection. To explore the potential of these characteristics, we take the perspective…
Accurate segmentation for medical images is important for clinical diagnosis. Existing automatic segmentation methods are mainly based on fully supervised learning and have an extremely high demand for precise annotations, which are very…
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…
Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are not widely employed. Annotating rotated bounding boxes is…
Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of…
With the rapid development of deep learning, object detection and tracking play a vital role in today's society. Being able to identify and track all the pedestrians in the dense crowd scene with computer vision approaches is a typical…
3D object detection with omnidirectional views enables safety-critical applications such as mobile robot navigation. Such applications increasingly operate on resource-constrained edge devices, facilitating reliable processing without…
Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression…
Visual object tracking is the problem of predicting a target object's state in a video. Generally, bounding-boxes have been used to represent states, and a surge of effort has been spent by the community to produce efficient causal…
Event-based cameras, inspired by the biological retina, have evolved into cutting-edge sensors distinguished by their minimal power requirements, negligible latency, superior temporal resolution, and expansive dynamic range. At present,…
Bounding-box regression is a popular technique to refine or predict localization boxes in recent object detection approaches. Typically, bounding-box regressors are trained to regress from either region proposals or fixed anchor boxes to…
We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…
Perceiving the complete shape of occluded objects is essential for human and machine intelligence. While the amodal segmentation task is to predict the complete mask of partially occluded objects, it is time-consuming and labor-intensive to…