Search results

This paper aims to propose the new incremental and parallel training algorithm of proximal support vector machines (Inc-Par-PSVM) tailored on the edge device (i.e. the Jetson Nano) to handle the large-scale ImageNet challenging problem.

The Inc-Par-PSVM trains in the incremental and parallel manner ensemble binary PSVM classifiers used for the One-Versus-All multiclass strategy on the Jetson Nano. The binary PSVM model is the average in bagged binary PSVM models built in undersampling training data block.

The empirical test results on the ImageNet data set show that the Inc-Par-PSVM algorithm with the Jetson Nano (Quad-core ARM A57 @ 1.43 GHz, 128-core NVIDIA Maxwell architecture-based graphics processing unit, 4 GB RAM) is faster and more accurate than the state-of-the-art linear SVM algorithm run on a PC [Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32 GB RAM].

The new incremental and parallel PSVM algorithm tailored on the Jetson Nano is able to efficiently handle the large-scale ImageNet challenge with 1.2 million images and 1,000 classes.

Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).

Two approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.

In Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.

An original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.

The use of unmanned aerial vehicles (UAVs) has significantly increased in the past decade and nowadays is being used for various purposes such as image processing, cargo transport, archaeology, agriculture, manufacturing, health care, surveillance and inspections. For this reason, using the appropriate image processing method for the intended use of UAVs increases the study’s success. This study aims to determine the most suitable one among the innovative methods that constitute the image processing system for a UAV to be used for surveillance purposes.

Analytical hierarchy process has been used in the solution of the decision problem to be handled in three stages, namely, platform, architecture and method. The most suitable alternative and the effect weights of these criteria results were determined at each stage.

As a result of this study, Jetson TX2 was determined as the most suitable embedded platform, ResNet is the optimum architecture and Faster R-convolutional neural networks was the best method in the image processing layer for a system that will provide surveillance with image processing method using UAV.

In UAV designs, where multiple hardware and software choices and system combinations exist, multi-criteria decision-making (MCDM) approaches can be used as a system decision mechanism.

The novelty of this work comes from the application of MCDM methods that are used as a multi-layered decision mechanism in UAV design.

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.

The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.

Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).

Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.

The purpose of this study is to test the Internet of things (IoT) devices with respect to reliability and quality.

In this paper, the authors have presented the analysis on design metrics such as perception, communication and computation layers for a constrained environment. In this paper, based on their literature survey, the authors have also presented a study that shows multipath routing is more efficient than single-path, and the retransmission mechanism is not preferable in an IoT environment.

This paper discusses the reliability of various layers of IoT subject methodologies used in those layers. The authors ran performance tests on Arduino nano and raspberry pi using the AES-128 algorithm. It was empirically determined that the time required to process a message increases exponentially and is more than what benchmark time estimates as the message size is increased. From these results, the authors can accurately determine the optimal size of the message that can be processed by an IoT system employing controllers, which are running 8-bit or 64-bit architectures.

The authors have tested the performance of standard security algorithms on different computational architectures and discuss the implications of the results. Empirical results demonstrate that encryption and decryption times increase nonlinearly rather than linearly as message size increases.

This work aims to present a deep learning model for face mask detection in surveillance environments such as automatic teller machines (ATMs), banks, etc. to identify persons wearing face masks. In surveillance environments, complete visibility of the face area is a guideline, and criminals and law offenders commit crimes by hiding their faces behind a face mask. The face mask detector model proposed in this work can be used as a tool and integrated with surveillance cameras in autonomous surveillance environments to identify and catch law offenders and criminals.

The proposed face mask detector is developed by integrating the residual network (ResNet)34 feature extractor on top of three You Only Look Once (YOLO) detection layers along with the usage of the spatial pyramid pooling (SPP) layer to extract a rich and dense feature map. Furthermore, at the training time, data augmentation operations such as Mosaic and MixUp have been applied to the feature extraction network so that it can get trained with images of varying complexities. The proposed detector is trained and tested over a custom face mask detection dataset consisting of 52,635 images. For validation, comparisons have been provided with the performance of YOLO v1, v2, tiny YOLO v1, v2, v3 and v4 and other benchmark work present in the literature by evaluating performance metrics such as precision, recall, F1 score, mean average precision (mAP) for the overall dataset and average precision (AP) for each class of the dataset.

The proposed face mask detector achieved 4.75–9.75 per cent higher detection accuracy in terms of mAP, 5–31 per cent higher AP for detection of faces with masks and, specifically, 2–30 per cent higher AP for detection of face masks on the face region as compared to the tested baseline variants of YOLO. Furthermore, the usage of the ResNet34 feature extractor and SPP layer in the proposed detection model reduced the training time and the detection time. The proposed face mask detection model can perform detection over an image in 0.45 s, which is 0.2–0.15 s lesser than that for other tested YOLO variants, thus making the proposed detection model perform detections at a higher speed.

The proposed face mask detector model can be utilized as a tool to detect persons with face masks who are a potential threat to the automatic surveillance environments such as ATMs, banks, airport security checks, etc. The other research implication of the proposed work is that it can be trained and tested for other object detection problems such as cancer detection in images, fish species detection, vehicle detection, etc.

The proposed face mask detector can be integrated with automatic surveillance systems and used as a tool to detect persons with face masks who are potential threats to ATMs, banks, etc. and in the present times of COVID-19 to detect if the people are following a COVID-appropriate behavior of wearing a face mask or not in the public areas.

The novelty of this work lies in the usage of the ResNet34 feature extractor with YOLO detection layers, which makes the proposed model a compact and powerful convolutional neural-network-based face mask detector model. Furthermore, the SPP layer has been applied to the ResNet34 feature extractor to make it able to extract a rich and dense feature map. The other novelty of the present work is the implementation of Mosaic and MixUp data augmentation in the training network that provided the feature extractor with 3× images of varying complexities and orientations and further aided in achieving higher detection accuracy. The proposed model is novel in terms of extracting rich features, performing augmentation at the training time and achieving high detection accuracy while maintaining the detection speed.

The purpose of the study is to address the problems of low accuracy and missed detection of occluded pedestrians and small target pedestrians when using the YOLOX general object detection algorithm for pedestrian detection. This study proposes a multi-level fine-grained YOLOX pedestrian detection algorithm.

First, to address the problem of the original YOLOX algorithm in obtaining a single perceptual field for the feature map before feature fusion, this study improves the PAFPN structure by adding the ResCoT module to increase the diversity of the perceptual field of the feature map and divides the pedestrian multi-scale features into finer granularity. Second, for the CSPLayer of the PAFPN, a weight gain-based normalization-based attention module (NAM) is proposed to make the model pay more attention to the context information when extracting pedestrian features and highlight the salient features of pedestrians. Finally, the authors experimentally determined the optimal values for the confidence loss function.

The experimental results show that, compared with the original YOLOX algorithm, the AP of the improved algorithm increased by 2.90%, the Recall increased by 3.57%, and F1 increased by 2% on the pedestrian dataset.

The multi-level fine-grained YOLOX pedestrian detection algorithm can effectively improve the detection of occluded pedestrians and small target pedestrians.

The authors introduce a multi-level fine-grained ResCoT module and a weight gain-based NAM attention module.

Magnet spot is the primary method to develop the automated guided vehicle (AGV) guidance system for many automated container terminals (ACT). Aiming to improve the high flexibility of AGV operation in ACT, this paper aims to address the problem of technical stability leading to ACT production paralysis and propose a mini-terminal AGV robot for testing laser simultaneous location and mapping (SLAM)-based methods in ACT operation scenarios.

This study developed a physical simulation robot for terminal AGV operations, providing a platform to test technical solutions for applying laser navigation-related technologies in ACTs. Then, the terminal-AGV navigation system framework is designed to apply the laser-SLAM-based method in the physical simulation robot. Finally, the experiment is conducted in the terminal operation scenario to verify the feasibility of the proposed framework for lased-SLAM-based method testing and analyze the performance of the different mini-terminal AGV robots.

A series of experiments are conducted to analyze the performance of the proposed mini-terminal AGV robot for laser-SLAM-based method testing. The experimental results show the validity and effectiveness of the AGV robot and AGV navigation system framework with better local map matching, loopback and absolute positional error.

The proposed mini-terminal AGV robot and AGV navigation system framework can provide a platform for innovative laser-SLAM-based method testing in ACTs applications. Therefore, this study can effectively meet the high requirements of ACT for maturity and stability of the laser navigation technical.

Robots equipped with LiDAR sensors can continuously perform efficient actions for mapping tasks to gradually build maps. However, with the complexity and scale of the environment increasing, the computation cost is extremely steep. This study aims to propose a hybrid autonomous exploration method that makes full use of LiDAR data, shortens the computation time in the decision-making process and improves efficiency. The experiment proves that this method is feasible.

This study improves the mapping update module and proposes a full-mapping approach that fully exploits the LiDAR data. Under the same hardware configuration conditions, the scope of the mapping is expanded, and the information obtained is increased. In addition, a decision-making module based on reinforcement learning method is proposed, which can select the optimal or near-optimal perceptual action by the learned policy. The decision-making module can shorten the computation time of the decision-making process and improve the efficiency of decision-making.

The result shows that the hybrid autonomous exploration method offers good performance, which combines the learn-based policy with traditional frontier-based policy.

This study proposes a hybrid autonomous exploration method, which combines the learn-based policy with traditional frontier-based policy. Extensive experiment including real robots is conducted to evaluate the performance of the approach and proves that this method is feasible.

This paper aims to develop a robust person tracking method for human following robots. The tracking system adopts the multimodal fusion results of millimeter wave (MMW) radars and monocular cameras for perception. A prototype of human following robot is developed and evaluated by using the proposed tracking system.

Limited by angular resolution, point clouds from MMW radars are too sparse to form features for human detection. Monocular cameras can provide semantic information for objects in view, but cannot provide spatial locations. Considering the complementarity of the two sensors, a sensor fusion algorithm based on multimodal data combination is proposed to identify and localize the target person under challenging conditions. In addition, a closed-loop controller is designed for the robot to follow the target person with expected distance.

A series of experiments under different circumstances are carried out to validate the fusion-based tracking method. Experimental results show that the average tracking errors are around 0.1 m. It is also found that the robot can handle different situations and overcome short-term interference, continually track and follow the target person.

This paper proposed a robust tracking system with the fusion of MMW radars and cameras. Interference such as occlusion and overlapping are well handled with the help of the velocity information from the radars. Compared to other state-of-the-art plans, the sensor fusion method is cost-effective and requires no additional tags with people. Its stable performance shows good application prospects in human following robots.