SMYOLO: Lightweight Pedestrian Target Detection Algorithm in Low-Altitude Scenarios

Due to the arbitrariness of the drone’s shooting angle of view and camera movement and the limited computing power of the drone platform, pedestrian detection in the drone scene poses a greater challenge. This paper proposes a new convolutional neural network structure, SMYOLO, which achieves the balance of accuracy and speed from three aspects: (1) By combining deep separable convolution and point convolution and replacing the activation function, the calculation amount and parameters of the original network are reduced; (2) by adding a batch normalization (BN) layer, SMYOLO accelerates the convergence and improves the generalization ability; and (3) through scale matching, reduces the feature loss of the original network. Compared with the original network model, SMYOLO reduces the accuracy of the model by only 4.36%, the model size is reduced by 76.90%, the inference speed is increased by 43.29%, and the detection target is accelerated by 33.33%, achieving minimization of the network model volume while ensuring the detection accuracy of the model.

A COMPREHENSIVE APPROACH INTO STEREOSCOPIC VISION

Stereopsis (or stereoscopic) vision is the ability to see depth of perception, which is created by the difference in angle of view between both eyes. The first process is known as simultaneous perception. Objects will fall on each corresponding retina and there will be a process of fusion of the two images into one. Then, the brain initiates three-dimensional perception in visual cortex, creating stereoscopic vision. Stereoscopic vision will rapidly develop, especially at the age of 6-8 months of life. Stereoscopic is important in daily activities. There are many stereoacuity tests to evaluate stereoscopic vision. Stereoscopic examinations are based on the principle of haploscope, anaglyph, or polaroid vectograph. There are qualitative and quantitative examination methods to assess stereoscopic vision. Qualitative examinations such as Horizontal Lang Two Pencil test and Synoptophore. Quantitative examination including Contour stereopsis test and Clinical random dot stereopsis test. The inability of the eye to see stereoscopic can be called stereoblindness. This can be affected by amblyopia, decreased visual acuity, or the presence of ocular misalignment. Inability to achieve stereoscopic vision will impact an individual to perform some daily life activities, and lead to an increase in difficulty interacting in the world.

Iterative tomography of pipes during operation

The pipe wall thickness was estimated based on three-dimensional images of the pipe recovered from several X-ray projections, which were made in a limited angle of view. Since the effects of scattered radiation and beam hardening are up to 50 % of the main radiation, ignoring them leads to blur of the image and inaccuracy in determining dimensions. To restore pipe images from projections, a volume and/or shell representation of the pipe is used, as well as iterative Bayesian methods. Using these methods, the error in estimating the pipe wall thickness from the projection data can be equal to or less than 300 μm. It has been shown that standard X-ray projections on the film or imaging plates used to obtain data can be used to restore pipe wall thickness profiles in factory conditions.

Consumers’ Journey between Liquid and Solid Consumption

Sharing economy brought changes both at the macroeconomic and the individual level. New models of consumption, such as the liquid one, are becoming very frequent, shaping countries’ productive systems and consumers’ habits. This paper—combining both theoretical approaches—aims at measuring the individual characteristics that induce consumers to prefer liquid versus solid consumption. First, the article contextualizes the topic from a broader, macroeconomic perspective, and later on, it narrows its angle of view making it rather microeconomic and behavioral. In this specific regard, by means of a cluster analysis, four profiles of consumers are identified: (1) Rational and liquid; (2) Hybrid and question mark; (3) Solid in transition; (4) Hyper solid. Characteristics as well as theoretical and managerial implications are outlined for each cluster. This research focusing on emerging consumer behavior contributes to the current debate on solid and liquid consumption (i) exploring the continuum between these two extremes, (ii) defining a first behavioral profile of customer that are traveling between solid and liquid state and (iii) designing a possible way to target such a blurred and fast evolving customer that mostly qualifies a global and rapidly evolving economic environment.

Point Projection Network: A Multi-View-Based Point Completion Network with Encoder-Decoder Architecture

Recently, unstructured 3D point clouds have been widely used in remote sensing application. However, inevitable is the appearance of an incomplete point cloud, primarily due to the angle of view and blocking limitations. Therefore, point cloud completion is an urgent problem in point cloud data applications. Most existing deep learning methods first generate rough frameworks through the global characteristics of incomplete point clouds, and then generate complete point clouds by refining the framework. However, such point clouds are undesirably biased toward average existing objects, meaning that the completion results lack local details. Thus, we propose a multi-view-based shape-preserving point completion network with an encoder–decoder architecture, termed a point projection network (PP-Net). PP-Net completes and optimizes the defective point cloud in a projection-to-shape manner in two stages. First, a new feature point extraction method is applied to the projection of a point cloud, to extract feature points in multiple directions. Second, more realistic complete point clouds with finer profiles are yielded by encoding and decoding the feature points from the first stage. Meanwhile, the projection loss in multiple directions and adversarial loss are combined to optimize the model parameters. Qualitative and quantitative experiments on the ShapeNet dataset indicate that our method achieves good results in learning-based point cloud shape completion methods in terms of chamfer distance (CD) error. Furthermore, PP-Net is robust to the deletion of multiple parts and different levels of incomplete data.

DisCaaS: Micro Behavior Analysis on Discussion by Camera as a Sensor

The emergence of various types of commercial cameras (compact, high resolution, high angle of view, high speed, and high dynamic range, etc.) has contributed significantly to the understanding of human activities. By taking advantage of the characteristic of a high angle of view, this paper demonstrates a system that recognizes micro-behaviors and a small group discussion with a single 360 degree camera towards quantified meeting analysis. We propose a method that recognizes speaking and nodding, which have often been overlooked in existing research, from a video stream of face images and a random forest classifier. The proposed approach was evaluated on our three datasets. In order to create the first and the second datasets, we asked participants to meet physically: 16 sets of five minutes data from 21 unique participants and seven sets of 10 min meeting data from 12 unique participants. The experimental results showed that our approach could detect speaking and nodding with a macro average f1-score of 67.9% in a 10-fold random split cross-validation and a macro average f1-score of 62.5% in a leave-one-participant-out cross-validation. By considering the increased demand for an online meeting due to the COVID-19 pandemic, we also record faces on a screen that are captured by web cameras as the third dataset and discussed the potential and challenges of applying our ideas to virtual video conferences.

Cooperative People Tracking by Distributed Cameras Network

In the application of video surveillance, reliable people detection and tracking are always challenging tasks. The conventional single-camera surveillance system may encounter difficulties such as narrow-angle of view and dead space. In this paper, we proposed multi-cameras network architecture with an inter-camera hand-off protocol for cooperative people tracking. We use the YOLO model to detect multiple people in the video scene and incorporate the particle swarm optimization algorithm to track the person movement. When a person leaves the area covered by a camera and enters an area covered by another camera, these cameras can exchange relevant information for uninterrupted tracking. The motion smoothness (MS) metrics is proposed for evaluating the tracking quality of multi-camera networking system. We used a three-camera system for two persons tracking in overlapping scene for experimental evaluation. Most tracking person offsets at different frames were lower than 30 pixels. Only 0.15% of the frames showed abrupt increases in offsets pixel. The experiment results reveal that our multi-camera system achieves robust, smooth tracking performance.

CERTAIN STATUS AND LABOR LAW ISSUES OF ELECTRONIC SPORT IN THE REPUBLIC OF SERBIA

The development of sports law has fundamentally changed the angle of view on the relationship between sports and law, which has long prevailed and manifested itself through the concept of denying the existence of the need to create special sports norms. With a critical approach and theoretical consideration, sports law has separated over time into a special branch of law that seeks to explain the essence of sports specificity, proving that the identity of sports norms arises precisely from the need for a broader view of relationships that arise in sports. As a distinctly social phenomenon, digitalization is beginning to have a strong influence on traditional sports concepts and the principles on which it is based, creating new forms of existence and practice of sports and leading to the emergence of e-sports. Due to the increasingly important role of e-sports in society, the work will be focused on the legal analysis of the position of e-sports in the sports system of the Republic of Serbia. Also, the authors will address the issue of the possibility of application or the need to change traditional principles in the field of sports to e-sports, which means pointing out the need to harmonize certain legal institutes related to e-sports in some places. The research will also include a review of labor and legal aspects of electronic sports, such as the possibility of signing contracts with persons under the age of 15, the possibility of signing contracts with athletes, etc. To answer the questions, we will start the analysis by defining the concept of sports and e-sports in the Republic of Serbia.