Locust Recognition and Detection via Aggregate Channel Features

Dewei Yi; Jinya Su; Wen-Hua Chen

Locust Recognition and Detection via Aggregate Channel Features

Dewei Yi, Jinya Su, Wen-Hua Chen

Loughborough University

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

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 language	English
Title of host publication	UK-RAS19 Conference
Subtitle of host publication	‘Embedded Intelligence: Enabling & Supporting RAS Technologies’ PROCEEDINGS
Place of Publication	Leicester, UK
Publisher	UK-RAS Network
Pages	112-115
Number of pages	4
Publication status	Published - 24 Jan 2019
Event	'Embedded Intelligence' UK-RAS19 Conference - Loughborough University, Loughborough, United Kingdom Duration: 24 Jan 2019 → 24 Jan 2019

Conference

Conference	'Embedded Intelligence' UK-RAS19 Conference
Country/Territory	United Kingdom
City	Loughborough
Period	24/01/19 → 24/01/19

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.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

https://www.ukras.org/publications/ras-proceedings/Licence: Unspecified

Cite this

Yi, D, Su, J & Chen, W-H 2019, Locust Recognition and Detection via Aggregate Channel Features. in UK-RAS19 Conference: ‘Embedded Intelligence: Enabling & Supporting RAS Technologies’ PROCEEDINGS. UK-RAS Network, Leicester, UK, pp. 112-115, 'Embedded Intelligence' UK-RAS19 Conference, Loughborough, United Kingdom, 24/01/19. <https://www.ukras.org/publications/ras-proceedings/>

@inproceedings{a254f42e2b404bec8a79105cceb49f44,

title = "Locust Recognition and Detection via Aggregate Channel Features",

abstract = "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.",

author = "Dewei Yi and Jinya Su and Wen-Hua Chen",

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.; 'Embedded Intelligence' UK-RAS19 Conference ; Conference date: 24-01-2019 Through 24-01-2019",

year = "2019",

month = jan,

day = "24",

language = "English",

pages = "112--115",

booktitle = "UK-RAS19 Conference",

publisher = "UK-RAS Network",

}

TY - GEN

T1 - Locust Recognition and Detection via Aggregate Channel Features

AU - Yi, Dewei

AU - Su, Jinya

AU - Chen, Wen-Hua

N1 - 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.

PY - 2019/1/24

Y1 - 2019/1/24

N2 - 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.

AB - 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.

M3 - Published conference contribution

SP - 112

EP - 115

BT - UK-RAS19 Conference

PB - UK-RAS Network

CY - Leicester, UK

T2 - 'Embedded Intelligence' UK-RAS19 Conference

Y2 - 24 January 2019 through 24 January 2019

ER -

Locust Recognition and Detection via Aggregate Channel Features

Abstract

Conference

Bibliographical note

UN SDGs

Access to Document

Fingerprint

Cite this