Deep Learning for Object Detection:A Survey

Object detection is one of the most important and challenging branches of computer vision,which has been widely applied in people s life,such as monitoring security,autonomous driving and so on,with the purpose of locating instances of semantic objects of a certain class.With the rapid development of deep learning algorithms for detection tasks,the performance of object detectors has been greatly improved.In order to understand the main development status of target detection,a comprehensive literature review of target detection and an overall discussion of the works closely related to it are presented in this paper.This paper various object detection methods,including one-stage and two-stage detectors,are systematically summarized,and the datasets and evaluation criteria used in object detection are introduced.In addition,the development of object detection technology is reviewed.Finally,based on the understanding of the current development of target detection,we discuss the main research directions in the future.

KSUTraffic: A Microscopic Traffic Simulator for Traffic Planning in Smart Cities

Simulation is a powerful tool for improving,evaluating and analyzing the performance of new and existing systems.Traffic simulators provide tools for studying transportation systems in smart cities as they describe the evolution of traffic to the highest level of detail.There are many types of traffic simulators that allow simulating traffic in modern cities.The most popular traffic simulation approach is the microscopic traffic simulation because of its ability to model traffic in a realistic manner.In many cities of Saudi Arabia,traffic management represents a major challenge as a result of expansion in traffic demands and increasing number of incidents.Unfortunately,employing simulation to provide effective traffic management for local scenarios in Saudi Arabia is limited to a number of commercial products in both public and private sectors.Commercial simulators are usually expensive,closed source and inflexible as they allow limited functionalities.In this project,we developed a local traffic simulator“KSUtraffic”for traffic modeling,planning and analysis with respect to different traffic control strategies and considerations.We modeled information specified by GIS and real traffic data.Furthermore,we designed experiments that manipulate simulation parameters and the underlying area.KSUTraffic visualizes traffic and provides statistical results on the simulated traffic which would help to improve traffic management and efficiency.

Survey on the Loss Function of Deep Learning in Face Recognition

With the continuous development of face recognition network,the selection of loss function plays an increasingly important role in improving accuracy.The loss function of face recognition network needs to minimize the intra-class distance while expanding the inter-class distance.So far,one of our mainstream loss function optimization methods is to add penalty terms,such as orthogonal loss,to further constrain the original loss function.The other is to optimize using the loss based on angular/cosine margin.The last is Triplet loss and a new type of joint optimization based on HST Loss and ACT Loss.In this paper,based on the three methods with good practical performance and the joint optimization method,various loss functions are thoroughly reviewed.