Research on small object detection methods based on deep learning

Kong, Yandan; Liu, Kai; Liang, Zhihong; Liu, Tiancheng; Huang, Yuxiang; Qin, Mingming

doi:10.1109/icpics55264.2022.9873614

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented results were developed from 2016 to 2018. In parallel to our work [186,187] noted that detecting objects at a distance is hard, and in particular human detection at a distance or in the presence of occlusions has gained popularity [188][189][190][191][192][193][194][195]. Further it has been noted by [196] that a number of human detection models do not generalize across datasets.…”

Section: Developments In the Fieldmentioning

confidence: 61%

Semantic Synthesis of Pedestrian Locomotion

Priisalu

Păduraru

Pirinen

et al. 2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large forward motion of the vehicle. Even object detection and human sensing models perform significantly worse on onboard videos when compared to standard benchmarks because objects often appear far away from the camera compared to the standard object detection benchmarks, image quality is often decreased by motion blur and occlusions occur often. This has led to the popularisation of traffic data-specific benchmarks. Recently Light Detection And Ranging (LiDAR) sensors have become popular to directly estimate depths without the need to perform 3D reconstructions. However, LiDAR-based methods still lack in articulated human detection at a distance when compared to image-based methods. We hypothesize that benchmarks targeted at articulated human sensing from LiDAR data could bring about increased research in human sensing and prediction in traffic and could lead to improved traffic safety for pedestrians.

show abstract