High-Efficiency Progressive Transmission and Automatic Recognition of Wildlife Monitoring Images With WISNs

Wenzhao Feng,Anqi Li,Weidong Bao,Junguo Zhang,Wenhua Ju

doi:10.1109/access.2019.2951596

Wenzhao Feng, Anqi Li + Show 3 more

Open Access

https://doi.org/10.1109/access.2019.2951596

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2019
Citations: 6	License type: CC BY 4.0

Affiliation: Beijing Forestry University

Abstract

Wireless image sensor networks (WISNs) are widely applied in wildlife monitoring, as they present a better performance in remote, real-time monitoring. However, traditional WISNs suffer from the limitations of low processing capability, power consumption restrictions and narrow transmission bandwidth. For the contradiction between the above limitations of WISNs and the wildlife monitoring images with high resolution and complex background, we propose a novel wildlife intelligent monitoring system. On the foundation of saliency object detection, the convolutional encoder-decoder network is utilized to realize the progressive compression transmission and restoration for wildlife monitoring images, which guarantees the transmission efficiency and quality of wildlife part. Moreover, to deal with the problems of high labor intensity, low efficiency and low recognition accuracy in classical manual sorting method, an improved Faster RCNN algorithm is proposed on the automatic recognition of wildlife images. The experimental results on our own wildlife dataset, show that the peak signal to noise ratio (PSNR) and structural similarity index (SSIM) are improved by 7.93%, 18.15% and 7.01%, 12.67% respectively on reconstruction image, when compared with the set partitioned in hierarchical tree (SPIHT) and embedded zerotree (EZW) algorithms. Compared with the traditional Faster RCNN algorithm, the recognition accuracy of six species wildlife is respectively improved by 1%, 18%, 5%, 17%, 2% and 19%, and the final mAP value reaches to 92.2% in test set increased by 10.9%, which demonstrates the proposed algorithm can ideally achieve the wildlife intelligent monitoring with WISNs.

Highlights

Wildlife resource is abundant in China and it significantly contributes to the balance and stability of the whole ecosystem [1]
WILDLIFE MONITORING SYSTEM WITH wireless image sensor networks (WISNs) WISNs is widely utilized in wildlife monitoring to capture and transmit wildlife image materials with industrial grade cameras, which consist of WISNs terminal nodes, coordination nodes, gateway nodes, control center and data processing module
Compared with the traditional Faster RCNN algorithm, the accuracy of the six wildlife species has been improved by 1%, 18%, 5%, 17%, 2% and 19% respectively, and the final mean average precision (mAP) value reaches to 92.2% which is increased by 10.9%

Summary

INTRODUCTION

Wildlife resource is abundant in China and it significantly contributes to the balance and stability of the whole ecosystem [1]. For transmitting task through resource-constrained WISNs, image compression coding is utilized to reduce the transmission workload and improve the transmission efficiency In this field, image compression algorithms such as static image compression coding standards: JEPG and JEPG2000 [7], [8], compressed sensing [9], discrete cosine transform [10], singular value decomposition [11] and deep convolutional neural network [12], are capable of achieving high-efficiency compression of image samples. Autoencoder [19], an unsupervised learning method is utilized in WISNs thanks to its simple structure This network architecture is only built upon standard components such as convolutional layers and skip connections [20], which can achieve the state-of-art performance in image compression and restoration tasks.

WILDLIFE MONITORING SYSTEM WITH WIS

IMAGE RECONSTRUCTION QUALITY

Findings

CONCLUSION