A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction.

Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions.

Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis.

Computer vision, biomedical image processing and deep learning are related fields with a tremendous impact on the interpretation of medical images today. Among biomedical image sensing modalities, ultrasound (US) is one of the most widely used in practice, since it is noninvasive, accessible, and cheap. Its main drawback, compared to other imaging modalities, like computed tomography (CT) or magnetic resonance imaging (MRI), consists of the increased dependence on the human operator. One important step toward reducing this dependence is the implementation of a computer-aided diagnosis (CAD) system for US imaging. The aim of the paper is to examine the application of contrast enhanced ultrasound imaging (CEUS) to the problem of automated focal liver lesion (FLL) diagnosis using deep neural networks (DNN). Custom DNN designs are compared with state-of-the-art architectures, either pre-trained or trained from scratch. Our work improves on and broadens previous work in the field in several aspects, e.g., a novel leave-one-patient-out evaluation procedure, which further enabled us to formulate a hard-voting classification scheme. We show the effectiveness of our models, i.e., 88% accuracy reported against a higher number of liver lesion types: hepatocellular carcinomas (HCC), hypervascular metastases (HYPERM), hypovascular metastases (HYPOM), hemangiomas (HEM), and focal nodular hyperplasia (FNH).

A PointNet-Based Solution for 3D Hand Gesture Recognition.

Gesture recognition is an intensively researched area for several reasons. One of the most important reasons is because of this technology's numerous application in various domains (e.g., robotics, games, medicine, automotive, etc.) Additionally, the introduction of three-dimensional (3D) image acquisition techniques (e.g., stereovision, projected-light, time-of-flight, etc.) overcomes the limitations of traditional two-dimensional (2D) approaches. Combined with the larger availability of 3D sensors (e.g., Microsoft Kinect, Intel RealSense, photonic mixer device (PMD), CamCube, etc.), recent interest in this domain has sparked. Moreover, in many computer vision tasks, the traditional statistic top approaches were outperformed by deep neural network-based solutions. In view of these considerations, we proposed a deep neural network solution by employing PointNet architecture for the problem of hand gesture recognition using depth data produced by a time of flight (ToF) sensor. We created a custom hand gesture dataset, then proposed a multistage hand segmentation by designing filtering, clustering, and finding the hand in the volume of interest and hand-forearm segmentation. For comparison purpose, two equivalent datasets were tested: a 3D point cloud dataset and a 2D image dataset, both obtained from the same stream. Besides the advantages of the 3D technology, the accuracy of the 3D method using PointNet is proven to outperform the 2D method in all circumstances, even the 2D method that employs a deep neural network.

Illumination normalization of face image based on illuminant direction estimation and improved Retinex.

Illumination normalization of face image for face recognition and facial expression recognition is one of the most frequent and difficult problems in image processing. In order to obtain a face image with normal illumination, our method firstly divides the input face image into sixteen local regions and calculates the edge level percentage in each of them. Secondly, three local regions, which meet the requirements of lower complexity and larger average gray value, are selected to calculate the final illuminant direction according to the error function between the measured intensity and the calculated intensity, and the constraint function for an infinite light source model. After knowing the final illuminant direction of the input face image, the Retinex algorithm is improved from two aspects: (1) we optimize the surround function; (2) we intercept the values in both ends of histogram of face image, determine the range of gray levels, and stretch the range of gray levels into the dynamic range of display device. Finally, we achieve illumination normalization and get the final face image. Unlike previous illumination normalization approaches, the method proposed in this paper does not require any training step or any knowledge of 3D face and reflective surface model. The experimental results using extended Yale face database B and CMU-PIE show that our method achieves better normalization effect comparing with the existing techniques.