scispace - formally typeset
G

Guanghui Wang

Researcher at Ryerson University

Publications -  176
Citations -  2971

Guanghui Wang is an academic researcher from Ryerson University. The author has contributed to research in topics: Object detection & Real image. The author has an hindex of 24, co-authored 173 publications receiving 2131 citations. Previous affiliations of Guanghui Wang include Nanchang University & Shenyang Institute of Automation.

Papers
More filters
Book ChapterDOI

VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results

Pengfei Zhu, +104 more
TL;DR: A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
Journal ArticleDOI

Learning Depth From Single Images With Deep Neural Network Embedding Focal Length

TL;DR: Zhang et al. as mentioned in this paper proposed a method to generate synthetic varying-focal-length data set from fixed-and varying focal length data sets, and a simple and effective method is implemented to fill the holes in the newly generated images.
Journal ArticleDOI

MDFN: Multi-scale deep feature learning network for object detection

TL;DR: This study reveals that deep features provide prominent semantic information and a variety of contextual contents, which contribute to its superior performance in detecting small or occluded objects.
Journal ArticleDOI

A comparative experimental study of image feature detectors and descriptors

TL;DR: This paper provides a comprehensive review of a large number of popular feature detectors developed in the last three decades and conducts comparisons of invariance against image transformations such as illumination changes, blurring, rotation, scaling, viewpoint changes, exposure, JPEG compression, combined scaling and rotation, and combined viewpoint changes.
Journal ArticleDOI

Vision-Based Real-Time Aerial Object Localization and Tracking for UAV Sensing System

TL;DR: In this article, a real-time object localization and tracking strategy from monocular image sequences is developed by effectively integrating the object detection and tracking into a dynamic Kalman model, where the object of interest is automatically detected and localized from a saliency map computed via the image background connectivity cue at each frame.