Accelerating Video Object Detection by Exploiting Prior Object Locations

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
3 Downloads (Pure)

Abstract

We provide a set of generic modifications to improve the execution efficiency of single-shot object detectors by exploiting prior object locations in video sequences. We propose a crop-based method to accelerate object detection tasks. It dynamically generates crop regions based on prior information and exploits scene sparsity enabling focused use of computational resources. In contrast to prior work, smaller input resolutions for processing crop regions are used to further reduce computational load. The execution efficiency is increased by avoiding multiple executions of the detector in full resolution. Data augmentations are used to successfully train these lower-resolution networks and maintain their accuracy at the baseline level while reducing inference time. Experiments with two public datasets, UA-DETRAC [13] and UAVDT [2], using the SSD-ML [19] object detection architecture with 128 × 128, 64 × 64 and 32 × 32 input resolutions show that we can achieve a maximum speedup by a factor of 1.7 on the UA-DETRAC dataset, and 1.6 on the UAVDT dataset while delivering the same level of accuracy as the base method. An extensive set of experiments demonstrates the speed-accuracy trade-off and shows that our method can achieve accuracy comparable to state-of-the-art methods at lower execution time.

Original languageEnglish
Title of host publicationImage Analysis and Processing – ICIAP 2022
Subtitle of host publication21st International Conference, Lecce, Italy, May 23–27, 2022, Proceedings, Part II
EditorsStan Sclaroff, Cosimo Distante, Marco Leo, Giovanni M. Farinella, Federico Tombari
PublisherSpringer
Chapter55
Pages657-668
Number of pages12
ISBN (Electronic)978-3-031-06430-2
ISBN (Print)978-3-031-06429-6
DOIs
Publication statusPublished - 2022
Event21st International Conference on Image Analysis and Processing, ICIAP 2022 - Lecce, Italy
Duration: 23 May 202227 May 2022
Conference number: 21

Publication series

NameLecture Notes in Computer Science (LNCS)
PublisherSpringer
Volume13232
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference21st International Conference on Image Analysis and Processing, ICIAP 2022
Abbreviated titleICIAP 2022
Country/TerritoryItaly
CityLecce
Period23/05/2227/05/22

Funding

This work is funded by the NWO Perspectief program ZERO.

Fingerprint

Dive into the research topics of 'Accelerating Video Object Detection by Exploiting Prior Object Locations'. Together they form a unique fingerprint.

Cite this