An Elephant Detection System to Prevent Human-Elephant Conflict and Tracking of Elephant Using Deep Learning

Premarathna, K. S. P.; Rathnayaka, R. M. K. T.; Joseph, Charles

doi:10.1109/icitr51448.2020.9310798

Cited by 22 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… In terms of model generalization capability, YOLOv5 adopts a mosaic data enhancement strategy to improve the generalization capability and robustness of the model [ 27 ]. Compared with the application of computer vision in the detection of other mammals (such as elephant (Elephantidae) [ 28 ] and golden monkey ( Rhinopithecus roxellana ) [ 29 ]), the performance of the proposed YOLOv5 CBAM + TC model in the detection of slow loris exceeds the average level and meets the needs of practical applications. The YOLOv5 CBAM + TC model was operated on a professional server in this study, but it can also be run smoothly on a common laptop, indicating that the model would be economical and practical in a real-world application.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Slow Loris Computer Vision Detection Model

Xiang

Zhu

et al. 2022

Animals

View full text Add to dashboard Cite

The slow loris (Genus Nycticebus) is a group of small, nocturnal and venomous primates with a distinctive locomotion mode. The detection of slow loris plays an important role in the subsequent individual identification and behavioral recognition and thus contributes to formulating targeted conservation strategies, particularly in reintroduction and post-release monitoring. However, fewer studies have been conducted on efficient and accurate detection methods of this endangered taxa. The traditional methods to detect the slow loris involve long-term observation or watching surveillance video repeatedly, which would involve manpower and be time consuming. Because humans cannot maintain a high degree of attention for a long time, they are also prone to making missed detections or false detections. Due to these observational challenges, using computer vision to detect slow loris presence and activity is desirable. This article establishes a novel target detection dataset based on monitoring videos of captive Bengal slow loris (N. bengalensis) from the wildlife rescue centers in Xishuangbanna and Pu’er, Yunnan, China. The dataset is used to test two improvement schemes based on the YOLOv5 network: (1) YOLOv5-CBAM + TC, the attention mechanism and deconvolution are introduced; (2) YOLOv5-SD, the small object detection layer is added. The results demonstrate that the YOLOv5-CBAM + TC effectively improves the detection effect. At the cost of increasing the model size by 0.6 MB, the precision rate, the recall rate and the mean average precision (mAP) are increased by 2.9%, 3.7% and 3.5%, respectively. The YOLOv5-CBAM + TC model can be used as an effective method to detect individual slow loris in a captive environment, which helps to realize slow loris face and posture recognition based on computer vision.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Compared with the application of computer vision in the detection of other mammals (such as elephant (Elephantidae) [ 28 ] and golden monkey ( Rhinopithecus roxellana ) [ 29 ]), the performance of the proposed YOLOv5 CBAM + TC model in the detection of slow loris exceeds the average level and meets the needs of practical applications.…”

Section: Discussionmentioning

confidence: 99%

Development of a Slow Loris Computer Vision Detection Model

Xiang

Zhu

et al. 2022

Animals

View full text Add to dashboard Cite

show abstract

“…Apart from these elephant restricting systems, there are several elephant intrusion detection systems employed in Asia and Africa. They use either the images/videos captured [7,8] or the infrasound calls generated by elephants [9,10] to detect the presence of an elephant. Nevertheless, the vision-based systems need to have a good visibility of the area without foliage cover which cannot be guaranteed in tropical Asian countries.…”

Section: Elephant Intrusion Minimizing Mechanismsmentioning

confidence: 99%

“…Method Accuracy (%) Image based [7] 92 Video based [8] 92.83 Infra-sound calls based [9] 88.2 Proposed 90…”

Section: Table 3 -Comparison Of Elephant Detection Accuraciesmentioning

confidence: 99%

“eleAlert”-A Sensor for Detecting Elephant Intrusions at Boundary Villages

2022

View full text Add to dashboard Cite

Human-elephant conflict (HEC) takes hundreds of human and elephant lives, every year. Though there are many techniques and systems deployed in African and Asian countries to mitigate this conflict, none of them have provided efficient solutions. The success of a modern HEC mitigating system heavily depends on its capability to detect the presence of an elephant. In most of the existing systems, their superior accuracy of detecting an elephant's presence is limited by certain conditions such as the ability to capture a good quality image containing the elephant. In this paper, we propose an alternative elephant detection system which uses odour of elephant urine and the earflap sound as detection parameters and also a support vector classification for decision making. The proposed system can produce higher accuracies in detecting wild elephants present in a 35m radius, under all conditions. Thus, the proposed system is much more superior over the existing elephant detection systems and will be an effective tool to mitigate the HEC.

show abstract

“…Current automated tools perform this work so quickly that they are used to send out real‐time alerts if humans or unknown vehicles are unexpectedly present in protected areas, offering rapid‐response opportunities for conservation teams on the ground (wpsWatch: Tuia et al, 2022). Similar systems inform local communities of the approach of potentially dangerous wildlife, such as elephants (Premarathna et al, 2020). Individual identification can present a particularly challenging problem for human coders.…”

Section: Introductionmentioning

confidence: 99%

DeepWild: Application of the pose estimation tool DeepLabCut for behaviour tracking in wild chimpanzees and bonobos

Wiltshire,

Lewis‐Cheetham,

Komedová

et al. 2023

Journal of Animal Ecology

View full text Add to dashboard Cite

Studying animal behaviour allows us to understand how different species and individuals navigate their physical and social worlds. Video coding of behaviour is considered a gold standard: allowing researchers to extract rich nuanced behavioural datasets, validate their reliability, and for research to be replicated. However, in practice, videos are only useful if data can be efficiently extracted. Manually locating relevant footage in 10,000 s of hours is extremely time‐consuming, as is the manual coding of animal behaviour, which requires extensive training to achieve reliability. Machine learning approaches are used to automate the recognition of patterns within data, considerably reducing the time taken to extract data and improving reliability. However, tracking visual information to recognise nuanced behaviour is a challenging problem and, to date, the tracking and pose‐estimation tools used to detect behaviour are typically applied where the visual environment is highly controlled. Animal behaviour researchers are interested in applying these tools to the study of wild animals, but it is not clear to what extent doing so is currently possible, or which tools are most suited to particular problems. To address this gap in knowledge, we describe the new tools available in this rapidly evolving landscape, suggest guidance for tool selection, provide a worked demonstration of the use of machine learning to track movement in video data of wild apes, and make our base models available for use. We use a pose‐estimation tool, DeepLabCut, to demonstrate successful training of two pilot models of an extremely challenging pose estimate and tracking problem: multi‐animal wild forest‐living chimpanzees and bonobos across behavioural contexts from hand‐held video footage. With DeepWild we show that, without requiring specific expertise in machine learning, pose estimation and movement tracking of free‐living wild primates in visually complex environments is an attainable goal for behavioural researchers.

show abstract

An Elephant Detection System to Prevent Human-Elephant Conflict and Tracking of Elephant Using Deep Learning

Cited by 22 publications

References 15 publications

Development of a Slow Loris Computer Vision Detection Model

Development of a Slow Loris Computer Vision Detection Model

“eleAlert”-A Sensor for Detecting Elephant Intrusions at Boundary Villages

DeepWild: Application of the pose estimation tool DeepLabCut for behaviour tracking in wild chimpanzees and bonobos

Contact Info

Product

Resources

About