Automatic detection of lizards

Nguwi, Yok-Yen; Kouzani, Abbas Z.; Kumar, Jayanth Jaya; Driscoll, Don A.

doi:10.1109/icamechs.2016.7813464

Cited by 4 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To census of endangered lizard species, it is important to automatically them from videos. In this context, Nguwi et al [264] used a background subtraction method to detect lizards in video, followed by experiments comparing thresholding values and methods.…”

Section: Lizards Surveillancementioning

confidence: 99%

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions

Bouwmans

García-García²

2019

Preprint

View full text Add to dashboard Cite

Computer vision applications based on videos often require the detection of moving objects in their first step. Background subtraction is then applied in order to separate the background and the foreground. In literature, background subtraction is surely among the most investigated field in computer vision providing a big amount of publications. Most of them concern the application of mathematical and machine learning models to be more robust to the challenges met in videos. However, the ultimate goal is that the background subtraction methods developed in research could be employed in real applications like traffic surveillance. But looking at the literature, we can remark that there is often a gap between the current methods used in real applications and the current methods in fundamental research. In addition, the videos evaluated in large-scale datasets are not exhaustive in the way that they only covered a part of the complete spectrum of the challenges met in real applications. In this context, we attempt to provide the most exhaustive survey as possible on real applications that used background subtraction in order to identify the real challenges met in practice, the current used background models and to provide future directions. Thus, challenges are investigated in terms of camera, foreground objects and environments. In addition, we identify the background models that are effectively used in these applications in order to find potential usable recent background models in terms of robustness, time and memory requirements.

show abstract

Section: Lizards Surveillancementioning

confidence: 99%

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions

Bouwmans

García-García²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Previous attempts using AI have been made [22]; however, they do not focus on ectothermic activity. Sophisticated algorithms determine changes in video frames, allowing for the analytical evaluation of object tracking, motion detection, and pattern recognition for endotherms and ectotherms [23,24]. Current video surveillance cameras often adopt an AI algorithm as the triggering method for recording video, as in our proposed camera trap.…”

Section: Introductionmentioning

confidence: 99%

A Smart Camera Trap for Detection of Endotherms and Ectotherms

Corva

Semianiw

Eichholtzer

et al. 2022

Sensors

View full text Add to dashboard Cite

Current camera traps use passive infrared triggers; therefore, they only capture images when animals have a substantially different surface body temperature than the background. Endothermic animals, such as mammals and birds, provide adequate temperature contrast to trigger cameras, while ectothermic animals, such as amphibians, reptiles, and invertebrates, do not. Therefore, a camera trap that is capable of monitoring ectotherms can expand the capacity of ecological research on ectothermic animals. This study presents the design, development, and evaluation of a solar-powered and artificial-intelligence-assisted camera trap system with the ability to monitor both endothermic and ectothermic animals. The system is developed using a central processing unit, integrated graphics processing unit, camera, infrared light, flash drive, printed circuit board, solar panel, battery, microphone, GPS receiver, temperature/humidity sensor, light sensor, and other customized circuitry. It continuously monitors image frames using a motion detection algorithm and commences recording when a moving animal is detected during the day or night. Field trials demonstrate that this system successfully recorded a high number of animals. Lab testing using artificially generated motion demonstrated that the system successfully recorded within video frames at a high accuracy of 0.99, providing an optimized peak power consumption of 5.208 W. No water or dust entered the cases during field trials. A total of 27 cameras saved 85,870 video segments during field trials, of which 423 video segments successfully recorded ectothermic animals (reptiles, amphibians, and arthropods). This newly developed camera trap will benefit wildlife biologists, as it successfully monitors both endothermic and ectothermic animals.

show abstract

Animal Biometrics: Concepts and Recent Application

Kumar¹,

Singh

et al. 2017

Animal Biometrics

View full text Add to dashboard Cite

Automatic detection of lizards

Cited by 4 publications

References 28 publications

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions

A Smart Camera Trap for Detection of Endotherms and Ectotherms

Animal Biometrics: Concepts and Recent Application

Contact Info

Product

Resources

About