Hand gesture recognition (HGR) takes a central role in human–computer interaction, covering a wide range of applications in the automotive sector, consumer electronics, home automation, and others. In recent years, accurate and efficient deep learning models have been proposed for real-time applications. However, the most accurate approaches tend to employ multiple modalities derived from RGB input frames, such as optical flow. This practice limits real-time performance due to intense extra computational cost. In this paper, we avoid the optical flow computation by proposing a real-time hand gesture recognition method based on RGB frames combined with hand segmentation masks. We employ a light-weight semantic segmentation method (FASSD-Net) to boost the accuracy of two efficient HGR methods: Temporal Segment Networks (TSN) and Temporal Shift Modules (TSM). We demonstrate the efficiency of the proposal on our IPN Hand dataset, which includes thirteen different gestures focused on interaction with touchless screens. The experimental results show that our approach significantly overcomes the accuracy of the original TSN and TSM algorithms by keeping real-time performance.

Recent works of real-time semantic segmentation, remove or make use of light decoders from dense deep neural networks to achieve fast inference speed. This strategy helps to achieve real-time performance; however, the accuracy is significantly compromised in comparison to non-real-time methods. In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation, which also reduces the accuracy gap between real-time and non-real-time networks. The first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. The second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses and refines detail and contextual information from multi-scale feature maps coming from early and deeper stages of the network. Both modules are designed to keep a low computational complexity by using asymmetric convolutions. With these modules, we propose a network entitled “FASSD-Net,” which is based on a light-weight CNN backbone. Running on a single Nvidia GTX 1080Ti, our model reaches 77.5% and 69.3% of mIoU, at 41 and 80 FPS on the Cityscapes and CamVid datasets, respectively. We present an extensive analysis of the accuracy-speed tradeoffs of three FASSD-Net variations on different embedded systems, demonstrating that a light version of our network can run on the low-power consumption Jetson Xavier NX, at 32 FPS reaching 74% of mIoU with full resolution ( $1024\times 2048$ ). The source code and pre-trained models are available at github.com/GibranBenitez/FASSD-Net.

Facial recognition is fundamental for a wide variety of security systems operating in real-time applications. Recently, several deep neural networks algorithms have been developed to achieve state-of-the-art performance on this task. The present work was conceived due to the need for an efficient and low-cost processing system, so a real-time facial recognition system was proposed using a combination of deep learning algorithms like FaceNet and some traditional classifiers like SVM, KNN, and RF using moderate hardware to operate in an unconstrained environment. Generally, a facial recognition system involves two main tasks: face detection and recognition. The proposed scheme uses the YOLO-Face method for the face detection task which is a high-speed real-time detector based on YOLOv3, while, for the recognition stage, a combination of FaceNet with a supervised learning algorithm, such as the support vector machine (SVM), is proposed for classification. Extensive experiments on unconstrained datasets demonstrate that YOLO-Face provides better performance when the face under an analysis presents partial occlusion and pose variations; besides that, it can detect small faces. The face detector was able to achieve an accuracy of over 89.6% using the Honda/UCSD dataset which runs at 26 FPS with darknet-53 to VGA-resolution images for classification tasks. The experimental results have demonstrated that the FaceNet+SVM model was able to achieve an accuracy of 99.7% using the LFW dataset. On the same dataset, FaceNet+KNN and FaceNet+RF achieve 99.5% and 85.1%, respectively; on the other hand, the FaceNet was able to achieve 99.6%. Finally, the proposed system provides a recognition accuracy of 99.1% and 49 ms runtime when both the face detection and classifications stages operate together.

Touchless in-car devices controlled by single and continuous finger gestures can provide comfort and safety on driving while manipulating secondary devices. Recognition of finger gestures is a challenging task due to (i) similarities between gesture and non-gesture frames, and (ii) the difficulty in identifying the temporal boundaries of continuous gestures. In addition, (iii) the intraclass variability of gestures’ duration is a critical issue for recognizing finger gestures intended to control in-car devices. To address difficulties (i) and (ii), we propose a gesture spotting method where continuous gestures are segmented by detecting boundary frames and evaluating hand similarities between the start and end boundaries of each gesture. Subsequently, we introduce a gesture recognition based on a temporal normalization of features extracted from the set of spotted frames, which overcomes difficulty (iii). This normalization enables the representation of any gesture with the same limited number of features. We ensure real-time performance by proposing an approach based on compact deep neural networks. Moreover, we demonstrate the effectiveness of our proposal with a second approach based on hand-crafted features performing in real-time, even without GPU requirements. Furthermore, we present a realistic driving setup to capture a dataset of continuous finger gestures, which includes more than 2,800 instances on untrimmed videos covering safety driving requirements. With this dataset, our both approaches can run at 53 fps and 28 fps on GPU and CPU, respectively, around 13 fps faster than previous works, while achieving better performance (at least 5% higher mean tIoU).

An increasing number of psychological studies have demonstrated that the six basic expressions of emotions are not culturally universal. However, automatic facial expression recognition (FER) systems disregard these findings and assume that facial expressions are universally expressed and recognized across different cultures. Therefore, this paper presents an analysis of Western-Caucasian and East-Asian facial expressions of emotions based on visual representations and cross-cultural FER. The visual analysis builds on the Eigenfaces method, and the cross-cultural FER combines appearance and geometric features by extracting Local Fourier Coefficients (LFC) and Facial Fourier Descriptors (FFD) respectively. Furthermore, two possible solutions for FER under multicultural environments are proposed. These are based on an early race detection, and independent models for culture-specific facial expressions found by the analysis evaluation. HSV color quantization combined with LFC and FFD compose the feature extraction for race detection, whereas culture-independent models of anger, disgust and fear are analyzed for the second solution. All tests were performed using Support Vector Machines (SVM) for classification and evaluated using five standard databases. Experimental results show that both solutions overcome the accuracy of FER systems under multicultural environments. However, the approach which individually considers the culture-specific facial expressions achieved the highest recognition rate.

Gesture spotting is an essential task for recognizing finger gestures used to control in-car touchless interfaces. Automated methods to achieve this task require to detect video segments where gestures are observed, to discard natural behaviors of users’ hands that may look as target gestures, and be able to work online. In this paper, we address these challenges with a recurrent neural architecture for online finger gesture spotting. We propose a multi-stream network merging hand and hand-location features, which help to discriminate target gestures from natural movements of the hand, since these may not happen in the same 3D spatial location. Our multi-stream recurrent neural network (RNN) recurrently learns semantic information, allowing to spot gestures online in long untrimmed video sequences. In order to validate our method, we collect a finger gesture dataset in an in-vehicle scenario of an autonomous car. 226 videos with more than 2100 continuous instances were captured with a depth sensor. On this dataset, our gesture spotting approach outperforms state-of-the-art methods with an improvement of about 10% and 15% of recall and precision, respectively. Furthermore, we demonstrated that by combining with an existing gesture classifier (a 3D Convolutional Neural Network), our proposal achieves better performance than previous hand gesture recognition methods.