相关论文: 3D Crowd Counting via Geometric Attention-guided M…

In the recent literature, on the one hand, many 3D multi-object tracking (MOT) works have focused on tracking accuracy and neglected computation speed, commonly by designing rather complex cost functions and feature extractors. On the other…

3D object detection is a common function within the perception system of an autonomous vehicle and outputs a list of 3D bounding boxes around objects of interest. Various 3D object detection methods have relied on fusion of different sensor…

Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications. In this paper, we propose a novel method using an attention model to exploit head…

Multi-view detection incorporates multiple camera views to alleviate occlusion in crowded scenes, where the state-of-the-art approaches adopt homography transformations to project multi-view features to the ground plane. However, we find…

3D object recognition has attracted wide research attention in the field of multimedia and computer vision. With the recent proliferation of deep learning, various deep models with different representations have achieved the…

This paper presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework. A Region Proposal Network (RPN) generates 3D proposals…

Accurate, real-time crowd counting on railway platforms is essential for safety and capacity management. We propose to use a single camera mounted in a train, scanning the platform while arriving. While hardware constraints are simple,…

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd…

In this paper, we tackle the problem of Crowd Counting, and present a crowd density estimation based approach for obtaining the crowd count. Most of the existing crowd counting approaches rely on local features for estimating the crowd…

The recent trend in 2D multiple object tracking (MOT) is jointly solving detection and tracking, where object detection and appearance feature (or motion) are learned simultaneously. Despite competitive performance, in crowded scenes, joint…

Detection-based methods have been viewed unfavorably in crowd analysis due to their poor performance in dense crowds. However, we argue that the potential of these methods has been underestimated, as they offer crucial information for crowd…

The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map. It also enlightens us back to the essence of the field, detection to count, which can…

State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to…

Three-dimensional Object Detection from multi-view cameras and LiDAR is a crucial component for autonomous driving and smart transportation. However, in the process of basic feature extraction, perspective transformation, and feature…

Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and…

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions,…

Crowd scenes captured by cameras at different locations vary greatly, and existing crowd models have limited generalization for unseen surveillance scenes. To improve the generalization of the model, we regard different surveillance scenes…

Accurately estimating the number of objects in a single image is a challenging yet meaningful task and has been applied in many applications such as urban planning and public safety. In the various object counting tasks, crowd counting is…

Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large domain gap between the two sensors in terms of coordinates…

Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds. To solve this issue, previous studies use 3D registration techniques. Out of these proposed techniques,…