Enhancing YOLOv3-tiny for Mask Detection in Natural Scenes

Person detection is an important prerequisite of social interaction, but is not well understood. Following suggestions that people in the visual field can capture a viewer's attention, this study examines the role of the face and the body for person detection in natural scenes. We observed that viewers tend first to look at the center of a scene, and only then to fixate on a person. When a person's face was rendered invisible in scenes, bodies were detected as quickly as faces without bodies, indicating that both are equally useful for person detection. Detection was optimized when face and body could be seen, but observers preferentially fixated faces, reinforcing the notion of a prominent role for the face in social perception. These findings have implications for claims of attention capture by faces in that they demonstrate a mediating influence of body cues and general scanning principles in natural scenes.

Text detection in natural scenes is fundamental for text image analysis. In this paper, we propose a context-based approach for robust and fast text detection. Our main contribution is that we introduce a new concept of key region, which is described with context according to stroke properties, appearance consistency and specific spatial distribution of text line. With such context descriptors, we adopt SVM to learn a context-based classifier to find key regions in candidate regions. Therein, candidate regions are connected components generated by local binarization algorithm in the areas, which are detected by an offline learned text patch detector. Experimental results on two benchmark datasets demonstrate that our approach has achieved competitive performances compared with the state-of-the-art algorithms including the stroke width transform (SWT) [1] and the hybrid approach based on CRFs [2] with speedup rates of about 1.7x~4.4x.

The object contour detection in natural scenes is an important research problem in computer vision. The difficulty is that the integrity of contour extracted is interfered with a large number of texture edges in the background seriously. In recent years, some researchers have introduced image contour detection method with biological visual features and achieved preferable results. Such as, based on the fact of visual outer region suppression, they can suppress a certain amount of texture edge while extracting the contour of the object, and obtain the proper contour edge. However, when this method is used for contour detection in some image which the texture is similar to the contour, the texture edge still cannot be removed well, and the result is unsatisfactory. In consideration of the merit and demerit of the feature suppressed method, we propose an improved algorithm for object contour detection in natural scene based on image saliency. Firstly, the initial contour is obtained by using the suppression effect of non-classical receptive field, and the saliency map is obtained by using the hyper-complex Fourier transform image saliency detection method, and then the initial contour and the saliency map are integrated into the final contour. Compared with the traditional contour detection method, the contour extraction algorithm based on image saliency can remove more background information and improve the accuracy and integrity of object contour extracted in natural scenes.

With the advancement of the times, the living conditions of people have improved significantly, and high-rise buildings and comprehensive buildings have risen from the ground. Once these buildings are caught in a fire or theft, they will cause great losses to people's life safety and property safety. There are many alarms on the market that solve security risks, but their functions are relatively single and the cost is high. This paper designs a fireproof and anti-theft intelligent alarm system based on a microcomputer to address the issues, using a smoke sensor, a temperature sensor, a pyroelectric infrared sensor to achieve fireproof and anti-theft functions. This paper analyses the requirements and the hardware circuit module of the fire and anti-theft system, designs the system software, and introduces the software design ideas. Based on simulation software, tests were carried out to verify the feasibility of the proposed design. The fireproof and anti-theft system in this paper can detect the leakage of combustible gases, the sudden rise in temperature and the function of human body intrusion, and automatically alarm. The system in this paper has low cost and can expand the function, which helps to protect people's lives and property safety, and has high practical significance.

A systematic comparison between visual cues for boundary detection

As an important core in the intelligent traffic management system, the technology and application of license plate recognition have become research focus. Detecting the accurate location of a license plate from a vehicle image is considered to be the most crucial step of license plate recognition, which greatly affects the recognition rate and speed of the whole system. Nevertheless, due to the low accuracy of license plate detection in natural scenes, further investigations are still needed in this field in order to make the detection process very efficient. In this paper, We have studied and implemented a convolutional neural network license plate detection algorithm based on transfer learning. According to the invention, new energy license plates and ordinary license plates are adopted as the research objects. The text detection model AdvancedEAST is trained on the license plate images through the transfer learning method, and experiments are carried out on the self-built license plate dataset. The experimental results show that the algorithm can better adapt to light complexity, low resolution, target interference, license plate tilt and other complex conditions. The license plate positioning algorithm has high accuracy in natural scenes, and it is superior to the traditional license plate detection methods.

Small object detection is a hard task to be sovled in object detection because the small object usually contain a few effective informations, which makes it very difficult to extract the discriminative features of small scale object. In addition, a key challenge in deep network for small object detectors is the large scale variation, where the performance of small object is poor due to the imbalanced optimization on various scale. In this paper, we propose a scale adaptive balance mechanism based on anchor-free framework for small object detection. Specifically, we design a new loss function to adapt the detection model to various object scale, which is able to alleviate the imbalance of object scale. Moreover, in feature extractor, the shallow feature maps of different receptive fields are added to the DLA-34 backbone for better extracting multi-scale features. Besides, the image block is used as a detection unit during inference, and the scale mismatch is thus overcome. Finally, the proposed method is verified on the Visdrone2019 dataset and the experimental results validate the effectiveness to detect small objects in the video image from drone monitoring.

With the development of the society, the demand of people's life safety, convenience is higher and higher. In this paper, the system, which is to designed a intelligent automatic induction door, used the microcontroller AT89S52 as the nucleus components, applied the pyroelectric infrared sensor as the detecting sensor, and four phase hybrid stepping motor as drive door. Meanwhile, the HC-SR501 human body induction module is selected in the design, which is composed the German import LHI778 type pyroelectric infrared sensor and dedicated BISS0001 processing chip. Finally, through the connected and download debug hard and soft, the result provides the system is safe and reliable, easy to operate.

Community epidemic prevention and control work is the first line to ensure people's life safety, and the improvement of community epidemic prevention and control ability is the key to ensure the implementation of various prevention and control measures. At present, China has made great strategic achievements in the fight against the COVID-19 epidemic, and the epidemic prevention and control work has turned into normal management. It still needs constant efforts to win a comprehensive victory in the war against the epidemic. Building community epidemic prevention and control mode with “Party building plus” as the core, classifying communities and implementing different prevention and control strategies, introducing Internet technology into epidemic prevention and control, and rallying community spirit to prevent and control forces are important practical experiences in this community epidemic prevention and control. However, as for the improvement of the prevention and control abilities of the communities, there are still difficulties of institutions, professionalism and technology. Based on the theory of community governance, this paper discusses the practical path to improve the ability of community epidemic prevention and control from the aspects of system standardization, prior work, professional construction, governance sinking, science and technology empowerment and spiritual cultivation.

Superhydrophobic materials used for anti-icing Theory, application, and development

Special articles refer to microorganisms, human tissues, biological products, blood and blood products in need of special management in entry administration. Such articles are related to national biological safety and people's life safety, and have always been the key regulatory objects in entry and exit inspection and quarantine. How to improve the efficiency of the inspection and quarantine supervision system has become the common aspiration of governments, enterprises, research institutes and other social sectors while ensuring the regulatory safety. On the basis of the original inspection and quarantine supervision system for special articles, this paper further improved the supervision and management process and established a more rigorous whole-process supervision system for special articles to better serve the social and economic development and scientific and technological progress while supervising the safety of special articles.

With the rapid development of the social economy, people's awareness of environmental protection is gradually increasing. This is because the probability of geographical disasters occurring in the country is also gradually increasing. People have also begun to pay attention to the prevention of geological disasters and the geological environment, because geological disasters can have a great impact on people's life safety at any time. Therefore, it is necessary to take corresponding preventive measures in advance for geological disasters. This article conducts a series of analyses on geological disasters and other related topics.

Identification of failure modes and paths of reservoir dams under explosion loads

Recent research on neocognitron-like neural feed-forward architectures, which have formerly been successfully applied to the recognition of artificial stimuli such as paperclip objects, now also opens up application to more natural stimuli. Such networks exhibit high-recognition performance with respect to translation, rotation, scaling and cluttered surroundings. In this contribution, we introduce a new type of hierarchical model, which is trained using a non-negative matrix factorization algorithm. In contrast to previous work, our approach cannot only classify objects but is also capable of rapid object detection in natural scenes. Thus, the time-consuming and conceptually unsatisfying split-up into a localization stage (e.g., using segmentation) and a subsequent classification can be avoided. The network consists of alternating layers of simple and complex cell planes and incorporates nonlinear processing schemes that have been proposed in recent literature. Learning of receptive field profiles for the lower layers of the network takes place by unsupervised learning whereas a final classification layer is trained supervised. This final layer is then utilized for detection. We test the classification performance of the network on images of natural objects which are systematically distorted. To test the ability to detect objects, cluttered natural background is used.

Text in images provides rich and accurate high-level semantic information, which is of great significance for many potential applications such as scene understanding, image and video retrieval. As a necessary means of understanding scene text, text detection has been widely concerned in the field of computer vision in recent years. However, due to the diversity of text scale and the uncertainty of image quality, text detection in natural scenes is still a challenging problem. Inspired by the successful application of deep neural network in target detection task, this paper proposes a text detection method based on multi-level feature extraction combined with deep learning technology. The multi-level feature extraction designed by this method can capture the details of the text, which is conducive to enhance the robustness of the algorithm to small-scale text and low-resolution images. In addition, the method is end-to-end, and can output text detection results directly. This paper evaluates the method on several standard datasets, and the experimental results prove the effectiveness of the proposed method.