Detection of Animals in Thermal Imagery for Surveillance using GAN and Object Detection Framework

Khatri, Khushboo; Asha, C S; D’Souza, Jeane Marina

doi:10.1109/iconat53423.2022.9725883

Cited by 8 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, using image processing and Mask R-CNN for counting animals, in [ 28 ], livestock, sheep and cattle are counted and classified, achieving a precision of 95.5% and

values of 95.2%, 95% and 95.4% for livestock, sheep and cattle, respectively. Using thermal images, animals such as dogs, cats, deer, rhinos, horses and elephants are detected and classified with an

of 75.98% with YOLOv3, 84.52% with YOLOv4 and 98.54% with Fast-RCNN [ 25 ]. In [ 24 ], the problem is turned into a classification as follows.…”

Section: Discussionmentioning

confidence: 99%

“…With non-wearable sensors, in [ 23 ], a system for tracking sheep that detects if they are standing or lying with infrared radiation cameras and computer vision techniques is proposed. Using video cameras and deep learning, wild animals can be successfully identified, counted and described [ 24 , 25 ] as well as other particular species such as Holstein Friesian cattle [ 26 ]. A quadcopter with a Mask R-CNN architecture has been used to detect and count cattle in both extensive production pastures and in feedlots with an accuracy of 94% [ 27 , 28 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vision-Based Module for Herding with a Sheepdog Robot

Castillo

Sánchez-González

Campazas-Vega

et al. 2022

Sensors

View full text Add to dashboard Cite

Livestock farming is assisted more and more by technological solutions, such as robots. One of the main problems for shepherds is the control and care of livestock in areas difficult to access where grazing animals are attacked by predators such as the Iberian wolf in the northwest of the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarks of animal images of different species from iNaturalist API, which is coupled with a vision-based module that allows us to automatically detect predators and distinguish them from other animals. We tested multiple existing object detection models to determine the best one in terms of efficiency and speed, as it is conceived for real-time environments. YOLOv5m achieves the best performance as it can process 64 FPS, achieving an mAP (with IoU of 50%) of 99.49% for a dataset where wolves (predator) or dogs (prey) have to be detected and distinguished. This result meets the requirements of pasture-based livestock farms.

show abstract

“…In addition, using image processing and Mask R-CNN for counting animals, in [ 28 ], livestock, sheep and cattle are counted and classified, achieving a precision of 95.5% and

values of 95.2%, 95% and 95.4% for livestock, sheep and cattle, respectively. Using thermal images, animals such as dogs, cats, deer, rhinos, horses and elephants are detected and classified with an

of 75.98% with YOLOv3, 84.52% with YOLOv4 and 98.54% with Fast-RCNN [ 25 ]. In [ 24 ], the problem is turned into a classification as follows.…”

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Vision-Based Module for Herding with a Sheepdog Robot

Castillo

Sánchez-González

Campazas-Vega

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…GANs are also capable of producing lifelike animal pictures. For instance, BigGAN, a GAN model created by Google researchers, can generate excellent pictures of animals like dogs and birds [10].…”

Section: Figure 1 General Architecture Of Generative Adversarial Networkmentioning

confidence: 99%

Real-Time Deepfake Image Generation Based on Stylegan2-ADA

Talib,

Abed

2023

RIA

View full text Add to dashboard Cite

Training Generative Adversarial Networks (GAN) usually leads to hyper-specialization due to few data and this causes training to diverge. This paper proposes a method that significantly stabilizes training without making changes. The method which will be used is stylegan2-ADA method to get fake images, the images will be entered in several steps, where the first step is using 76,400 Flickr-Faces-HQ (FFHQ) images and training them to get fake images. The program will be dividing images inside seven test folders, as the performance rate of 1000 images is 83.3%, which is a very good percentage when compared with the stylegan2 method because our proposed method contains augmentation that generates many images through the use of few images. The second step is represented by using personal images, we used two personal images and made a projection between them. The result of the performance of generating 200 images is 99.9%. Additionally, will be took a direct photo using the computer camera in real-time mode, and i generated 300 images. The generation performance is 99.9%, and our approach outperformed earlier ones in terms of accuracy, the ability to produce images without noise, and ability to create fake images of people who are not actually there.

show abstract

“…Generative Adversarial Networks (GANs) and, in particular, conditional GAN (cGAN) [81] have demonstrated their effectiveness in a variety of tasks in the agricultural domain including remote sensing [82], image augmentation [83], animal farming [84], and plant phenotyping [85]. The general idea of GAN is based on the usage of two neural network models, where the first network is called generator (generative part, G) and its goal is to create plausible samples, while the second network is called discriminator (adversarial part, D), and it learns to verify whether the created plausible sample is real or fake.…”

Section: Gan-based Models For Rgb and Nir Data Analysismentioning

confidence: 99%

Deep Learning in Precision Agriculture: Artificially Generated VNIR Images Segmentation for Early Postharvest Decay Prediction in Apples

Stasenko

Shukhratov

Savinov

et al. 2023

Entropy

View full text Add to dashboard Cite

Food quality control is an important task in the agricultural domain at the postharvest stage for avoiding food losses. The latest achievements in image processing with deep learning (DL) and computer vision (CV) approaches provide a number of effective tools based on the image colorization and image-to-image translation for plant quality control at the postharvest stage. In this article, we propose the approach based on Generative Adversarial Network (GAN) and Convolutional Neural Network (CNN) techniques to use synthesized and segmented VNIR imaging data for early postharvest decay and fungal zone predictions as well as the quality assessment of stored apples. The Pix2PixHD model achieved higher results in terms of VNIR images translation from RGB (SSIM = 0.972). Mask R-CNN model was selected as a CNN technique for VNIR images segmentation and achieved 58.861 for postharvest decay zones, 40.968 for fungal zones and 94.800 for both the decayed and fungal zones detection and prediction in stored apples in terms of F1-score metric. In order to verify the effectiveness of this approach, a unique paired dataset containing 1305 RGB and VNIR images of apples of four varieties was obtained. It is further utilized for a GAN model selection. Additionally, we acquired 1029 VNIR images of apples for training and testing a CNN model. We conducted validation on an embedded system equipped with a graphical processing unit. Using Pix2PixHD, 100 VNIR images from RGB images were generated at a rate of 17 frames per second (FPS). Subsequently, these images were segmented using Mask R-CNN at a rate of 0.42 FPS. The achieved results are promising for enhancing the food study and control during the postharvest stage.

show abstract

Detection of Animals in Thermal Imagery for Surveillance using GAN and Object Detection Framework

Cited by 8 publications

References 22 publications

Vision-Based Module for Herding with a Sheepdog Robot

Vision-Based Module for Herding with a Sheepdog Robot

Real-Time Deepfake Image Generation Based on Stylegan2-ADA

Deep Learning in Precision Agriculture: Artificially Generated VNIR Images Segmentation for Early Postharvest Decay Prediction in Apples

Contact Info

Product

Resources

About