Image Detection and Recognition of different species of animals using Deep Learning

Shanthakumari, R.; Nalini, C.; Vinothkumar, S.; Govindaraj, B.; Dharani, S.; Chindhana, S.

doi:10.1109/mecon53876.2022.9752203

Cited by 11 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We solve the proposed model with globally optimal guarantee. Extensive experiments on challenging well-known data sets demonstrate that our method significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex scenarios [6] This paper will discuss the present level of research and development on humanwildlife conflicts, there are bad interactions between humans and wild animals that are bad for both the resources of the human population as well as the ecosystems of wildlife. Animal detection has an impact on both human food security and animal welfare because it arises from the conflict between humans and wildlife over natural resources.…”

Section: Analysis and Visualizationmentioning

confidence: 99%

Intelligent Image-Based Defense Against Incursion from The Wild Animals

Dr.R.T.Ajaykarthik,

R.Arunbabu,

K.Aditya

et al. 2024

Int Res J Adv Engg Hub

View full text Add to dashboard Cite

A revolutionary development in agricultural security, Smart Crop Guardian is designed expressly to counter invasions from wild animals. This system merges cutting-edge sensors and powerful algorithms to give an all-encompassing defense mechanism for crops by utilizing cutting-edge image-based technologies. Smart Crop Guardian continuously monitors the environment to detect and track wildlife hazards in real time, enabling prompt intervention and reducing possible harm. This abstract explores the salient characteristics and advantages of Smart Crop Guardian, showcasing its potential to transform crop protection techniques. The core of Smart Crop Guardian is its intelligent image-based skills, which let it distinguish between environmental conditions that aren't a concern and real threats from wild animals. The technology achieves a high degree of accuracy in recognizing trespassing wildlife through the use of high-resolution cameras and sophisticated image processing algorithms. Furthermore, Smart Crop Guardian interacts effortlessly with current monitoring infrastructure, resulting in a cost-effective solution that maximizes the utility of pre-existing equipment. Because of its versatility, it is a viable alternative for a wide range of agricultural contexts, from small-scale farms to large commercial enterprises. The system's user-friendly interface streamlines monitoring, allowing farmers and security professionals to handle and respond to possible threats more efficiently. In addition to providing instant protection, Smart Crop Guardian promotes sustainable farming practices by eliminating the need for conventional deterrents, which can have negative environmental consequences. The approach minimizes disturbances to the natural ecosystem while protecting important crops by accurately directing interventions. Finally, Smart Crop Guardian is a game changer in agricultural security, providing sophisticated image-based protection against wild animal invasions. Its superior technology, seamless integration, and environmentally friendly approach make it a useful asset in current farming practices, offering improved crop security and less environmental effect.

show abstract

Section: Analysis and Visualizationmentioning

confidence: 99%

Intelligent Image-Based Defense Against Incursion from The Wild Animals

Dr.R.T.Ajaykarthik,

R.Arunbabu,

K.Aditya

et al. 2024

Int Res J Adv Engg Hub

View full text Add to dashboard Cite

show abstract

“…Energy consumption is a critical issue in the design of wireless underwater sensor networks (WUSNs). Data transfer in the harsh underwater channel requires higher transmission powers compared to an equivalent terrestrial-based network to achieve the same range [6]. However, batteryoperated underwater sensor nodes are energyconstrained and require that they transmit with low power to conserve power.…”

Section: Since Communications In the Underwatermentioning

confidence: 99%

Underwater Visible Light Communication for Scuba Divers Health Monitoring System

Dr.R.T. Ajaykarthik,

Kamalesh.N,

Naveen.V

et al. 2024

Int Res J Adv Engg Hub

View full text Add to dashboard Cite

Diving has become a common way of performing research in the underwater living world. One of the major problems with diving is the health issues faced by the divers during diving and there comes the need for monitoring diver’s health. This paper mainly focuses on the health monitoring systems for divers by transferring the data using Li-Fi (Light Fidelity). This system senses different health specifications like heartbeat, body temperature and body position. The monitored health specifications are recorded as a database in a memory chip for further analysis. To reduce the power consumption, the system transfers the data to the nearby divers and ships only during the abnormal health issue. The uniqueness of this system lies in its combination of advanced technologies for diver safety, communication, and submarine surveillance. This is crucial for ensuring their safety, especially in challenging underwater environments. This is perhaps one of the most unique aspects. Li-Fi, which uses light to transmit data, is a breakthrough for underwater communication. This system provides real-time data on the diver's condition and an immediate way to request assistance in case of an emergency. By incorporating temperature and gyro monitoring, the system collects valuable data on diver conditions and movements. This data could be analyzed for research or used to improve safety protocols in the future.

show abstract

“…If we use images captured on different dates as training and testing datasets, the accuracy drops dramatically to less than 10%. Shanthakumari R et al [16] A high-precision animal identification method based on YOLOv5 is proposed. First, a dataset of animals containing 80 different types of malformations is collected.…”

Section: Introductionmentioning

confidence: 99%

RTDETR-Refa: a real-time detection method for multi-breed classiffcation of cattle

Li,

Fang,

Zhao

2024

Preprint

View full text Add to dashboard Cite

In the farming industry in order to cope with the problems such as the complex environment of the pasture and dense targets, etc., which lead to increased difficulty in recognition, so as to quickly classify and automatically identify cattle breeds and improve the accuracy. In this paper, an RTDETR-Refa (Rep- Conv Efficient Faster Attention) model is proposed for classification and identification of cattle breeds. Firstly, some novel improvements have been made to ResNet18. Replacing the 1×1 convolution in Faster-Block with the reparameterised RepConv, and adding the Efficient Multiscale Attention Module (EMA) in front of the global average pooling layer in Faster-Block to enhance the transformation and classification of features, Finally, the 4-layer BasicBlock after the 3 convolutional layers in the resnet18-backbone is replaced by the improved Faster-Block.Finally, the results of the training tests of the RTDETR-Refa model are compared with other classical models: the YOLO family of models: the YOLOv5m, YOLOv6, YOLOv8m, YOLOv9 and the state-of-the-art (SOTA) CNN backbone networks EfficientViT, FasterNet, UniRepLKNet, TransNeXt verifying their superiority. The average accuracy of the RTDETR-Refa model on the cattle classification training set is 91.6%, which is 0.8% higher than that of ResNet18 and 0.9-5.2% higher than that of other classical models. The experimental results show that the RTDETR-Refa model proposed in this paper is capable of identifying and classifying cattle of different breeds while ensuring similar detection speeds, demonstrating the feasibility of convolutional neural networks in breed identification and classification.

show abstract

Image Detection and Recognition of different species of animals using Deep Learning

Cited by 11 publications

References 15 publications

Intelligent Image-Based Defense Against Incursion from The Wild Animals

Intelligent Image-Based Defense Against Incursion from The Wild Animals

Underwater Visible Light Communication for Scuba Divers Health Monitoring System

RTDETR-Refa: a real-time detection method for multi-breed classiffcation of cattle

Contact Info

Product

Resources

About