On-Board Small-Scale Object Detection for Unmanned Aerial Vehicles (UAVs)

Saeed, Zubair; Yousaf, Muhammad Haroon; Ahmed, Rehan; Velastín, Sergio A.; Viriri, Serestina

doi:10.3390/drones7050310

Cited by 16 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the results attained are compared with the ones achieved by the Small-Scale Object Detection for Unmanned Aerial Vehicles (UAVs) system proposed by Saeed et al which modified the architecture of the detection network and executed on different embedded systems, as we present early our system can detect and locate the object in the surveillance area in the real-time [50]. Singhal and Barick also proposes an application-aware Multi-Path Weighted Load-balancing (MWL) routing protocol for managing congestion, this system executes its process in the ground center, which increases the processing time and makes it out of service and powerless in the event of interruption or penetration [51].…”

Section: Methodsmentioning

confidence: 99%

Security Surveillance Using UAVs and Embedded Systems in Industrial Areas

Mezouari,

Benaly,

El Karch

et al. 2024

IJSSE

View full text Add to dashboard Cite

This paper proposes a novel security surveillance Unmanned Aerial Vehicle (UAV) that can handle security in large industrial areas with increased surveillance efficiency. Our basic idea is that Unmanned Aerial Vehicle sighting can be treated as a motion detection problem in the surveillance area by detecting position and type simultaneously when the Unmanned Aerial Vehicle flies in the 360° detection area. To reach our target, this paper proposes a mathematical approach based on camera calibration, ordinal distortion correction, and three-dimensional reconstruction that can help us determine the exact position of a moving object in the monitored area. It is also important to recognize movements and their character and to determine their position on the ground, all of this must be done in Real-time with short processing times. The outcomes of our study demonstrate that system processing average duration and processing system consumption have slightly decreased with the utilization of the Raspberry Pi+VPU system compared to alternatives such as the Jetson Nano, Raspberry Pi 4 boards, clusters, and personal computers. This underscores the effectiveness of our proposed system in terms of processing efficiency and resource utilization.

show abstract

Section: Methodsmentioning

confidence: 99%

Security Surveillance Using UAVs and Embedded Systems in Industrial Areas

Mezouari,

Benaly,

El Karch

et al. 2024

IJSSE

View full text Add to dashboard Cite

show abstract

“…To validate the deployment of our method on UAVs, we compared it with several commonly used edge devices [46]. Among them, Nvidia Jetson Nano, as a typical low-power and smallsized edge computing platform, is widely used.…”

Section: Uavs Deploymentmentioning

confidence: 99%

A novel efficient wildlife detecting method with lightweight deployment on UAVs based on YOLOv7

Mou,

Zhu,

Liu

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Efficient animal detection is essential for biodiversity protection. Unmanned aerial vehicles (UAVs) have been widely used because of their low costs and minimal environmental intrusion. However, using UAVs for practical animal detection poses two challenges: (a) the UAV's fly highly to avoid disturbing animals, resulting in small object detection problems; (b) the limited processing power of UAVs makes large state‐of‐the‐art (SOTA) methods (e.g., You Only Look Once V7, YOLOv7) difficult to deploy. This work proposes the WILD‐YOLO based on YOLOv7 to deal with the two problems. To detect small objects, WILD‐YOLO improves upon YOLOv7 by adding a small object detection head in the head part. To enable real‐time animal detection in field environments with UAVs, the lighten FasterNet and GhostNet have been used to significantly reduce the model size. Compared to YOLOv7, WILD‐YOLO significantly reduces the number of parameters, making it suitable for lightweight deployment on UAVs. Additionally, comparisons with other lightweight models such as YOLOv7‐tiny, YOLOv5‐s, YOLOv4‐s and MobilenetV2 on the datasets are conducted. The experimental results demonstrate that this proposed WILD‐YOLO method outperforms other approaches and has great potential for effective detection of wildlife in complex environments encountered by UAVs.

show abstract

“…This extensive connection mitigates the vanishing gradient issue that deep neural networks often encounter and allows optimal parameter reuse. Additionally, DenseNet architectures can be improved for feature extractors for a variety of image recognition tasks [25][26][27] because they have already been pre-trained on large datasets, i.e., ImageNet. By removing the fully connected layers and substituting identity functions, the DenseNet121 model is used in the given study as a feature extractor which turns it into a feature extraction module.…”

Section: Features Extractionmentioning

confidence: 99%

Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach

Saeed,

Bouhali,

et al. 2024

Bioengineering

Self Cite

View full text Add to dashboard Cite

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging is critical for successful treatment and patient survival. However, manual diagnosis by radiologist experts is time-consuming and has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts of medical data for early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as a promising tool for understanding diseases like brain cancer through medical imaging modalities, especially MRI, which provides detailed soft tissue contrast for visualizing tumors and organs. DL techniques have become more and more popular in current research on brain tumor detection. Unlike traditional machine learning methods requiring manual feature extraction, DL models are adept at handling complex data like MRIs and excel in classification tasks, making them well-suited for medical image analysis applications. This study presents a novel Dual DCNN model that can accurately classify cancerous and non-cancerous MRI samples. Our Dual DCNN model uses two well-performed DL models, i.e., inceptionV3 and denseNet121. Features are extracted from these models by appending a global max pooling layer. The extracted features are then utilized to train the model with the addition of five fully connected layers and finally accurately classify MRI samples as cancerous or non-cancerous. The fully connected layers are retrained to learn the extracted features for better accuracy. The technique achieves 99%, 99%, 98%, and 99% of accuracy, precision, recall, and f1-scores, respectively. Furthermore, this study compares the Dual DCNN’s performance against various well-known DL models, including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, and LeNet-5, with different learning rates. This study indicates that our proposed approach outperforms these established models in terms of performance.

show abstract

On-Board Small-Scale Object Detection for Unmanned Aerial Vehicles (UAVs)

Cited by 16 publications

References 38 publications

Security Surveillance Using UAVs and Embedded Systems in Industrial Areas

Security Surveillance Using UAVs and Embedded Systems in Industrial Areas

A novel efficient wildlife detecting method with lightweight deployment on UAVs based on YOLOv7

Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach

Contact Info

Product

Resources

About