University of Twente Student Theses


Increasing the accuracy of rodent detection and estimation of the population with emerging sensor technology

Dadhich, Shrasti (2023) Increasing the accuracy of rodent detection and estimation of the population with emerging sensor technology.

[img] PDF
Abstract:Rodents are the largest and most diverse taxonomic group of mammals, with over 2200 recognized species and recent estimates claiming the number to be close to 2500 [11]. A wide number of these rodents pose significant threats to agriculture, human health, and infrastructure. In this paper, we present a novel method for detecting and capturing rodents using a combination of sensor technologies. The detection and estimation of the rodent population are achieved using Radar sensors. At the same time, a Raspberry Pi camera and Ultrasonic microphone are employed to capture images and recordings of rodents inside the trap. PIR sensors are used to activate the radar, camera, and microphone when the presence of rodents is detected. Images captured with the Raspberry Pi camera are further classified with the YOLOV4 method providing mean average precision of 95 percent. In the last experiment conducted for the SPYCE project [45], rodent detection was performed with the PIR sensor.It shows that PIR has a detection range of up to 3m. The results provided in this paper improve detection up to 10m with Radar. It implements the counting of the rodents with Cm wave Radar providing 0.8 counting accuracy. It also facilitates the recording of rodents’ voices with ultrasonic microphones and images for further identification of rodents. This paper presents the design of a trap station to fulfill the project’s requirements. A literature survey has been performed to guide the implementation of the trap station, enhancing the detection of rodents. Additionally, radar point clouds are used to track the movement of rats in open spaces. This research’s findings demonstrate the proposed method’s effectiveness by combining the sensor technology in detecting and capturing rodents while facilitating their identification for further research and conservation efforts.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Programme:Embedded Systems MSc (60331)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page