Locust Recognition and Detection via Aggregate Channel Features

Dewei Yi, Jinya Su, Wen-Hua Chen

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution


Locust plagues are very harmful for food security, quality and quantity of agricultural products. With this consideration, precise locust detection is significant for preventing locust plagues. To achieve this task, aggregate channel feature (ACF) object detector with parameters optimization is applied to detect locusts. Experiment results show that ACF object detector with optimized parameters can achieve 0.39 for average precision and 0.86 for log-average miss rate. Moreover, ACF is a non-deep method using a simple model to detect objects. That is, the proposed method is promising to be embedded in a real-time locust detection system.
Original languageEnglish
Title of host publicationUK-RAS19 Conference
Subtitle of host publication‘Embedded Intelligence: Enabling & Supporting RAS Technologies’ PROCEEDINGS
Place of PublicationLeicester, UK
PublisherUK-RAS Network
Number of pages4
Publication statusPublished - 24 Jan 2019
Event'Embedded Intelligence' UK-RAS19 Conference - Loughborough University, Loughborough, United Kingdom
Duration: 24 Jan 201924 Jan 2019


Conference'Embedded Intelligence' UK-RAS19 Conference
Country/TerritoryUnited Kingdom

Bibliographical note

This work was supported by the U.K. Science and Technology Facilities
Council under Grant ST/N006852/1, ST/N006712/1, and ST/N006836/1.


Dive into the research topics of 'Locust Recognition and Detection via Aggregate Channel Features'. Together they form a unique fingerprint.

Cite this