DisCountNet: Discriminating and Counting Network for Real-Time Counting and Localization of Sparse Objects in High-Resolution UAV Imagery

Rahnemoonfar, Maryam; Dobbs, Dugan; Yari, Masoud; Starek, Michael J.

doi:10.3390/rs11091128

Cited by 34 publications

(33 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible solution to this problem is to sweep the entire image using a sliding window in such a way each animal will appear, at least partially, in multiple image blocks to be analyzed by the model. This approach, which has been explored by [15,17,18], enables the construction of a heat map showing the likely positions of the animals in the image. The problem with this approach is that the number of image blocks to be analyzed may be very high; on the other hand, applying the models is much faster than training them, which makes this approach adequate in many situations.…”

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…All methods for cattle detection using deep learning found in the literature use one of two methods. The first approach uses CNNs to generate a probability heat map which hopefully shows where animals are located [15,17,18]. The second approach uses techniques that generate a bounding box around the objects of interest [19,22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Barbedo¹,

Koenigkan²,

Santos³

et al. 2019

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Barbedo¹,

Koenigkan²,

Santos³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Although in the last few years the number of studies dedicated to cattle has risen, they are still relatively rare. A few academic investigations on this subject have been dedicated to animal detection and counting [15][16][17][18][19], cattle round-up [20], feeding behavior [21], animal identification [22] and health monitoring [23]. Most of those studies (especially the most recent ones) employ deep learning for animal detection.…”

Section: Introductionmentioning

confidence: 99%

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

Barbedo

Koenigkan

Santos

et al. 2019

Sensors

View full text Add to dashboard Cite

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.

show abstract

“…In recent years, the research community has witnessed advances in artificial intelligence (AI). Recent advances in deep neural networks (DNNs) and massive datasets have facilitated progress in AI tasks such as classification [7][8][9][10], object recognition [11,12], counting [13][14][15], contour and edge detection [16] and semantic segmentation [17][18][19]. Despite this progress, these algorithms are limited to cases where large labeled datasets are available.…”

Section: Introductionmentioning

confidence: 99%

AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network

Rahnemoonfar

Johnson

Paden

2019

Sensors

Self Cite

View full text Add to dashboard Cite

Significant resources have been spent in collecting and storing large and heterogeneous radar datasets during expensive Arctic and Antarctic fieldwork. The vast majority of data available is unlabeled, and the labeling process is both time-consuming and expensive. One possible alternative to the labeling process is the use of synthetically generated data with artificial intelligence. Instead of labeling real images, we can generate synthetic data based on arbitrary labels. In this way, training data can be quickly augmented with additional images. In this research, we evaluated the performance of synthetically generated radar images based on modified cycle-consistent adversarial networks. We conducted several experiments to test the quality of the generated radar imagery. We also tested the quality of a state-of-the-art contour detection algorithm on synthetic data and different combinations of real and synthetic data. Our experiments show that synthetic radar images generated by generative adversarial network (GAN) can be used in combination with real images for data augmentation and training of deep neural networks. However, the synthetic images generated by GANs cannot be used solely for training a neural network (training on synthetic and testing on real) as they cannot simulate all of the radar characteristics such as noise or Doppler effects. To the best of our knowledge, this is the first work in creating radar sounder imagery based on generative adversarial network.

show abstract

DisCountNet: Discriminating and Counting Network for Real-Time Counting and Localization of Sparse Objects in High-Resolution UAV Imagery

Cited by 34 publications

References 46 publications

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

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

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

AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network

Contact Info

Product

Resources

About