CNN-Based Intelligent Safety Surveillance in Green IoT Applications

Safety surveillance is considered one of the most important factors in many constructing industries for green internet of things(IoT)applications.However,traditional safety monitoring methods require a lot of labor source.In this paper,we propose intelligent safety surveillance(ISS)method using a convolutional neural network(CNN),which is an autosupervised method to detect workers whether or not wearing helmets.First,to train the CNN-based ISS model,the labeled datasets mainly come from two aspects:1)our labeled datasets with the full labeled on both helmet and pedestrian;2)public labeled datasets with the parts labeled either on the helmet or pedestrian.To fully take advantage of all datasets,we redesign CNN structure of network and loss functions based on YOLOv3.Then,we test our proposed ISS method based on the specific detection evaluation metrics.Finally,experimental results are given to show that our proposed ISS method enables the model to fully learn the labeled information from all datasets.When the threshold of intersection over union(IoU)between the predicted box and ground truth is set to 0.5,the average precision of pedestrians and helmets can reach 0.864 and 0.891,respectively.

Guest Editorial:Intelligent Video Surveillance and Related Technologies

Due to the increasing demand for developing a secure and smart living environment, the intelligent video surveillance technology has attracted considerable attention. Building an automatic, reliable, secure, and intelligent video surveillance system has spawned large research projects and triggered many popular research topics in several international conferences and workshops recently. This special issue of Journal of ElecWonic Science and Technology （JEST） aims to present recent advances in video surveillance systems which address the observation of people in an environment, leading to a real-time description of their actions and interactions.

A light-weight on-line action detection with hand trajectories for industrial surveillance

Most of the intelligent surveillances in the industry only care about the safety of the workers.It is meaningful if the camera can know what,where and how the worker has performed the action in real time.In this paper,we propose a light-weight and robust algorithm to meet these requirements.By only two hands'trajectories,our algorithm requires no Graphic Processing Unit(GPU)acceleration,which can be used in low-cost devices.In the training stage,in order to find potential topological structures of the training trajectories,spectral clustering with eigengap heuristic is applied to cluster trajectory points.A gradient descent based algorithm is proposed to find the topological structures,which reflects main representations for each cluster.In the fine-tuning stage,a topological optimization algorithm is proposed to fine-tune the parameters of topological structures in all training data.Finally,our method not only performs more robustly compared to some popular offline action detection methods,but also obtains better detection accuracy in an extended action sequence.

Ob ject Tracking with Dual Field-of-view Switching in Aerial Videos

Visual object tracking plays an important role in intelligent aerial surveillance by unmanned aerial vehicles（UAV）. In ordinary applications, aerial videos are captured by cameras with a fixed-focus lens or a zoom lens, for which the field-of-view（FOV）of the camera is fixed or smoothly changed. In this paper, a special application of the visual tracking in aerial videos captured by the dual FOV camera is introduced, which is different from ordinary applications since the camera quickly switches its FOV during the capturing. Firstly, the tracking process with the dual FOV camera is analyzed, and a conclusion is made that the critical part for the whole process depends on the accurate tracking of the target at the moment of FOV switching. Then, a cascade mean shift tracker is proposed to deal with the target tracking under FOV switching. The tracker utilizes kernels with multiple bandwidths to execute mean shift locating, which is able to deal with the abrupt motion of the target caused by FOV switching. The target is represented by the background weighted histogram to make it well distinguished from the background, and a modification is made to the weight value in the mean shift process to accelerate the convergence of the tracker. Experimental results show that our tracker presents a good performance on both accuracy and efficiency for the tracking. To the best of our knowledge, this paper is the first attempt to apply a visual object tracking method to the situation where the FOV of the camera switches in aerial videos.

Crowdmodeling based on purposiveness and a destination-driven analysis method

This study focuses on the multiphase flow properties of crowd motions.Stability is a crucial forewarning factor for the crowd.To evaluate the behaviors of newly arriving pedestrians and the stability of a crowd,a novel motion structure analysis model is established based on purposiveness,and is used to describe the continuity of pedestrians’pursuing their own goals.We represent the crowd with self-driven particles using a destination-driven analysis method.These self-driven particles are trackable feature points detected from human bodies.Then we use trajectories to calculate these self-driven particles’purposiveness and select trajectories with high purposiveness to estimate the common destinations and the inherent structure of the crowd.Finally,we use these common destinations and the crowd structure to evaluate the behavior of newly arriving pedestrians and crowd stability.Our studies show that the purposiveness parameter is a suitable descriptor for middle-density human crowds,and that the proposed destination-driven analysis method is capable of representing complex crowd motion behaviors.Experiments using synthetic and real data and videos of both human and animal crowds have been conducted to validate the proposed method.

Research on Video Object Detection Methods Based on YOLO with Motion Features

Aiming at the fixed-view video surveillance scene,this paper proposes a video object detection method that combines motion features and YOLO.The method uses the method of filtering video frames without motion features and segmenting video frames with motion features to reduce the reasoning pressure of the YOLO algorithm model.In this process,video frames containing moving objects are first obtained by the moving object detection module.Second,the moving target will be recognized by the object of interest recognition module.Finally,the background decision module records and analyzes the detection results to obtain background model updates or result output.It detects moving objects without using traditional background modeling methods.Experiments based on theCDnet2014 dataset showthat our method improves the missed detection rate by 0.098% and the average inference speed per frame by 45.62%compared with the YOLO-based humanoid detection method.Furthermore,the method has superior performance in scenarios where target objects appear less frequently(substations,transmission lines,and hazardous areas).