Autonomous Human-Vehicle Leader-Follower Control Using Deep-Learning-Driven Gesture Recognition

Schulte, Joseph; Kocherovsky, Mark; Paul, Nicholas; Pleune, Mitchell; Chung, Chan-Jin

doi:10.3390/vehicles4010016

Cited by 8 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous Computer-Aided Diagnosis (CAD) systems have been developed in the past and are continually evolving to aid radiologists in the diagnosis of breast cancer [8]. Developments in the recent past have made it possible to deploy Artificial Intelligence (Al)-based CAD systems in various fields, including medical image diagnosis [9], precision agriculture [10], natural language processing [11], and gesture recognition [12]. Deep learning (DL) has resolved the issues related to manual processing of visual information, the conventional method of feature extraction, that had been faced by researchers in the past.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Automated Technique for Classification of Breast Cancer Using Deep Ensemble Model

Rehman¹,

Ahmad²,

Jaha³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Breast cancer is one of the leading cancers among women. It has the second-highest mortality rate in women after lung cancer. Timely detection, especially in the early stages, can help increase survival rates. However, manual diagnosis of breast cancer is a tedious and time-consuming process, and the accuracy of detection is reliant on the quality of the images and the radiologist's experience. However, computer-aided medical diagnosis has recently shown promising results, leading to the need to develop an efficient system that can aid radiologists in diagnosing breast cancer in its early stages. The research presented in this paper is focused on the multi-class classification of breast cancer. The deep transfer learning approach has been utilized to train the deep learning models, and a pre-processing technique has been used to improve the quality of the ultrasound dataset. The proposed technique utilizes two deep learning models, Mobile-NetV2 and DenseNet201, for the composition of the deep ensemble model. Deep learning models are fine-tuned along with hyperparameter tuning to achieve better results. Subsequently, entropy-based feature selection is used. Breast cancer identification using the proposed classification approach was found to attain an accuracy of 97.04%, while the sensitivity and F1 score were 96.87% and 96.76%, respectively. The performance of the proposed model is very effective and outperforms other state-of-the-art techniques presented in the literature.

show abstract

Section: Introductionmentioning

confidence: 99%

An Efficient Automated Technique for Classification of Breast Cancer Using Deep Ensemble Model

Rehman¹,

Ahmad²,

Jaha³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…The most efficient means of natural expression that everyone is familiar with is the hand gesture interaction. A wide range of applications have taken place in HRI systems, including virtual mouse control [16], gaming technology for enhancing motor skills [17], sign language recognition [18], and human-vehicle interaction [19].…”

Section: Introductionmentioning

confidence: 99%

An Integrated Real-Time Hand Gesture Recognition Framework for Human–Robot Interaction in Agriculture

et al. 2022

View full text Add to dashboard Cite

Incorporating hand gesture recognition in human–robot interaction has the potential to provide a natural way of communication, thus contributing to a more fluid collaboration toward optimizing the efficiency of the application at hand and overcoming possible challenges. A very promising field of interest is agriculture, owing to its complex and dynamic environments. The aim of this study was twofold: (a) to develop a real-time skeleton-based recognition system for five hand gestures using a depth camera and machine learning, and (b) to enable a real-time human–robot interaction framework and test it in different scenarios. For this purpose, six machine learning classifiers were tested, while the Robot Operating System (ROS) software was utilized for “translating” the gestures into five commands to be executed by the robot. Furthermore, the developed system was successfully tested in outdoor experimental sessions that included either one or two persons. In the last case, the robot, based on the recognized gesture, could distinguish which of the two workers required help, follow the “locked” person, stop, return to a target location, or “unlock” them. For the sake of safety, the robot navigated with a preset socially accepted speed while keeping a safe distance in all interactions.

show abstract

“…Hand and other body part tracking from digital photographs has transformed not only the scientific world, but also the entertainment business, such as gaming and animation. It also replaced traditional hard labor in fields like as factory automation, virtual reality, rehabilitation and handicap support, performance monitoring, and many others [2]. There are now methods in which a user can have unique hardware connected to his or her body that allows for accurate study of the joints and geometry of body components.…”

Section: Introductionmentioning

confidence: 99%

Detection of hand gestures with human computer recognition by using support vector machine

Al-Juboori¹,

Almutairi²,

Almajed³

et al. 2022

PEN

View full text Add to dashboard Cite

Many applications, such as interactive data analysis and sign detection, can benefit from hand gesture recognition. We offer a low-cost approach based on human-computer interaction for predicting hand movements in real time. Our technique involves using a color glove to train a random forest classifier and then predicting a naked hand at the pixel level. Our algorithm anticipates all pixels at a rate of around 3 frames per second and is unaffected by differences in the surroundings. It's also been proven that HCI-based data augmentation is more effective than any other way for enhancing interactive data. In addition, the augmentation experiment was carried out on multiple subsets of the original hand skeleton sequence dataset, each with a different number of classes, as well as on the entire dataset. On practically all subsets, the proposed base architecture improved classification accuracy. When the entire dataset was used, there was even a modest improvement. Correct identification could be regarded as a quality indicator. The best accuracy score was 94.02 percent for the HCI-model with support vector machine (SVM) classifier.

show abstract

Autonomous Human-Vehicle Leader-Follower Control Using Deep-Learning-Driven Gesture Recognition

Cited by 8 publications

References 17 publications

An Efficient Automated Technique for Classification of Breast Cancer Using Deep Ensemble Model

An Efficient Automated Technique for Classification of Breast Cancer Using Deep Ensemble Model

An Integrated Real-Time Hand Gesture Recognition Framework for Human–Robot Interaction in Agriculture

Detection of hand gestures with human computer recognition by using support vector machine

Contact Info

Product

Resources

About