Battery-Powered Wild Animal Detection Nodes with Deep Learning

2020 ◽  
Vol E103.B (12) ◽  
pp. 1394-1402
Author(s):  
Hiroshi SAITO ◽  
Tatsuki OTAKE ◽  
Hayato KATO ◽  
Masayuki TOKUTAKE ◽  
Shogo SEMBA ◽  
...  
Keyword(s):  
Deep Learning ◽  
Wild Animal ◽  
Animal Detection

Deep neural networks for animal object detection and recognition in the wild

2019 ◽  
Author(s):  
◽  
Hayder Yousif
Keyword(s):  
Deep Learning ◽  
Animal Species ◽  
Object Segmentation ◽  
Camera Trap ◽  
Background Modeling ◽  
Camera Traps ◽  
Natural Scene ◽  
Feature Maps ◽  
Object Proposals ◽  
Animal Detection

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Camera traps are a popular tool to sample animal populations because they are noninvasive, detect a variety of species, and can record many thousands of animal detections per deployment. Cameras are typically set to take bursts of multiple images for each detection, and are deployed in arrays of dozens or hundreds of sites, often resulting in millions of images per study. The task of converting images to animal detection records from such large image collections is daunting, and made worse by situations that generate copious empty pictures from false triggers (e.g. camera malfunction or moving vegetation) or pictures of humans. We offer the first widely available computer vision tool for processing camera trap images. Our results show that the tool is accurate and results in substantial time savings for processing large image datasets, thus improving our ability to monitor wildlife across large scales with camera traps. In this dissertation, we have developed new image/video processing and computer vision algorithms for efficient and accurate object detection and sequence-level classiffication from natural scene camera-trap images. This work addresses the following five major tasks: (1) Human-animal detection. We develop a fast and accurate scheme for human-animal detection from highly cluttered camera-trap images using joint background modeling and deep learning classification. Specifically, first, We develop an effective background modeling and subtraction scheme to generate region proposals for the foreground objects. We then develop a cross-frame image patch verification to reduce the number of foreground object proposals. Finally, We perform complexity-accuracy analysis of deep convolutional neural networks (DCNN) to develop a fast deep learning classification scheme to classify these region proposals into three categories: human, animals, and background patches. The optimized DCNN is able to maintain high level of accuracy while reducing the computational complexity by 14 times. Our experimental results demonstrate that the proposed method outperforms existing methods on the camera-trap dataset. (2) Object segmentation from natural scene. We first design and train a fast DCNN for animal-human-background object classification, which is used to analyze the input image to generate multi-layer feature maps, representing the responses of different image regions to the animal-human-background classifier. From these feature maps, we construct the so-called deep objectness graph for accurate animal-human object segmentation with graph cut. The segmented object regions from each image in the sequence are then verfied and fused in the temporal domain using background modeling. Our experimental results demonstrate that our proposed method outperforms existing state-of-the-art methods on the camera-trap dataset with highly cluttered natural scenes. (3) DCNN domain background modeling. We replaced the background model with a new more efficient deep learning based model. The input frames are segmented into regions through the deep objectness graph then the region boundaries of the input frames are multiplied by each other to obtain the regions of movement patches. We construct the background representation using the temporal information of the co-located patches. We propose to fuse the subtraction and foreground/background pixel classiffcation of two representation : a) chromaticity and b) deep pixel information. (4) Sequence-level object classiffcation. We proposed a new method for sequence-level video recognition with application to animal species recognition from camera trap images. First, using background modeling and cross-frame patch verification, we developed a scheme to generate candidate object regions or object proposals in the spatiotemporal domain. Second, we develop a dynamic programming optimization approach to identify the best temporal subset of object proposals. Third, we aggregate and fuse the features of these selected object proposals for efficient sequence-level animal species classification.

Wild animal survey using UAS imagery and deep learning: modified Faster R-CNN for kiang detection in Tibetan Plateau

2020 ◽  
Vol 169 ◽  
pp. 364-376
Author(s):  
Jinbang Peng ◽  
Dongliang Wang ◽  
Xiaohan Liao ◽  
Quanqin Shao ◽  
Zhigang Sun ◽  
...  
Keyword(s):  
Deep Learning ◽  
Tibetan Plateau ◽  
Wild Animal

scholarly journals A tribrid Paradigm against Inundation wild animal attack and fire disasters

2019 ◽  
Vol 9 (2S3) ◽  
pp. 454-457
Keyword(s):  
Disaster Management ◽  
Fire Detection ◽  
Wild Animal ◽  
Red Cross ◽  
Remedial Action ◽  
The Common ◽  
Government Records ◽  
Animal Detection ◽  
Detection Unit ◽  
Animal Attack

In recent years the whole world witnessed several natural and manmade disasters. 2015 Earthquake in Nepal and India with 7.8 magnitudes which killed 9000 people and injured 22000 as per Government Records. 2018 Flood in North Korea left 10,700 people as per the report of International Federation of Red Cross (IFRC) and Wikipedia. Floods in India 2018, killed more than 300 in the state of Kerala. 2016, Forest fire in Uttarakhand, India burnt 10,000 acres of Forest area. In between April 2014 – May 2017, 1,144 people killed by wild animals as per the report of Indian Environment Ministry (IEM). All the reports stated above represents indications that regardless of several advancements and technical skill development to disaster management is not considered efficiently worldwide. There are plenty of disasters which could be taken care of much efficiently and wisely. If we see the disasters like flood, fire and animal attack we can easily notice that they are manageable to much extent with expert technical advancements. Our paper is about the disaster management of the tribrid series (Flood, Fire, Wild Animal Attack) with the eminent usage of technology. We create a flood sensing unit, a fire detection unit, and a wild animal detection unit with the help of sensors and we create the alert and remedial action unit to protect the common men from sub disasters. We use Embedded and IOT technologies together to provide worldwide coverage and accurate detection of the calamities.

scholarly journals A Study on the Detection of Cattle in UAV Images Using Deep Learning

2019 ◽  
Author(s):  
Jayme Garcia Arnal Barbedo ◽  
Luciano Vieira Koenigkan ◽  
Thiago Teixeira Santos ◽  
Patrícia Menezes Santos
Keyword(s):  
Deep Learning ◽  
Bos Taurus ◽  
Relevant Information ◽  
Learning Technologies ◽  
Aerial Images ◽  
Ground Sample ◽  
Bos Taurus Indicus ◽  
Uav Images ◽  
Production Areas ◽  
Animal Detection

Unmanned Aerial Vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and Convolutional Neural Networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: 1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (\textit{Bos taurus indicus}); 2) to determine the ideal Ground Sample Distance (GSD) for animal detection; 3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1,853 images containing 8,629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures * 3 spacial resolutions * 2 datasets * 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring.

scholarly journals A Study on the Detection of Cattle in UAV Images Using Deep Learning

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5436 ◽  
Author(s):  
Jayme Garcia Arnal Barbedo ◽  
Luciano Vieira Koenigkan ◽  
Thiago Teixeira Santos ◽  
Patrícia Menezes Santos
Keyword(s):  
Deep Learning ◽  
Bos Taurus ◽  
Relevant Information ◽  
Learning Technologies ◽  
Aerial Images ◽  
Ground Sample ◽  
Bos Taurus Indicus ◽  
Uav Images ◽  
Production Areas ◽  
Animal Detection

Unmanned aerial vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and convolutional neural networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: (1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (Bos taurus indicus); (2) to determine the ideal ground sample distance (GSD) for animal detection; (3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1853 images containing 8629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures × 3 spacial resolutions × 2 datasets × 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring.

Sign in / Sign up

Export Citation Format

Share Document