Next Article in Journal
Wearable Accelerometer and sEMG-Based Upper Limb BSN for Tele-Rehabilitation
Next Article in Special Issue
Periodic Surface Defect Detection in Steel Plates Based on Deep Learning
Previous Article in Journal
A Brief Theoretical Analysis on the Ventilation Characteristics of the Multi-Intake-Well Air Supply System in a Spillway Tunnel
Previous Article in Special Issue
CP-SSD: Context Information Scene Perception Object Detection Based on SSD
Open AccessArticle

An Integrated Wildlife Recognition Model Based on Multi-Branch Aggregation and Squeeze-And-Excitation Network

by Jiangjian Xie 1,2, Anqi Li 1,2, Junguo Zhang 1,2,* and Zhean Cheng 1,2
School of Technology, Beijing Forestry University, Beijing 100083, China
Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(14), 2794;
Received: 29 May 2019 / Revised: 25 June 2019 / Accepted: 9 July 2019 / Published: 12 July 2019
(This article belongs to the Special Issue Computer Vision and Pattern Recognition in the Era of Deep Learning)
Infrared camera trapping, which helps capture large volumes of wildlife images, is a widely-used, non-intrusive monitoring method in wildlife surveillance. This method can greatly reduce the workload of zoologists through automatic image identification. To achieve higher accuracy in wildlife recognition, the integrated model based on multi-branch aggregation and Squeeze-and-Excitation network is introduced. This model adopts multi-branch aggregation transformation to extract features, and uses Squeeze-and-Excitation block to adaptively recalibrate channel-wise feature responses based on explicit self-mapped interdependencies between channels. The efficacy of the integrated model is tested on two datasets: the Snapshot Serengeti dataset and our own dataset. From experimental results on the Snapshot Serengeti dataset, the integrated model applies to the recognition of 26 wildlife species, with the highest accuracies in Top-1 (when the correct class is the most probable class) and Top-5 (when the correct class is within the five most probable classes) at 95.3% and 98.8%, respectively. Compared with the ROI-CNN algorithm and ResNet (Deep Residual Network), on our own dataset, the integrated model, shows a maximum improvement of 4.4% in recognition accuracy. View Full-Text
Keywords: wildlife recognition; SE-ResNeXt; deep convolutional neural network wildlife recognition; SE-ResNeXt; deep convolutional neural network
Show Figures

Figure 1

MDPI and ACS Style

Xie, J.; Li, A.; Zhang, J.; Cheng, Z. An Integrated Wildlife Recognition Model Based on Multi-Branch Aggregation and Squeeze-And-Excitation Network. Appl. Sci. 2019, 9, 2794.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Search more from Scilit
Back to TopTop