This paper focuses on smoke detection in forest environments. In this paper, dark channel prior and OTSU based multi-threshold are used to find the disturbances such as sky and haze. These regions are blocked to reduc...
This paper focuses on smoke detection in forest environments. In this paper, dark channel prior and OTSU based multi-threshold are used to find the disturbances such as sky and haze. These regions are blocked to reduce false alarm rate. A motion detection method based on frame difference is adapted to find the motion objects. Color moments, HOG and LBP are chosen as features of smoke and SVM is used as the classification. To reduce more false alarms, the motion regions are classified for several consecutive frames. They won't be regarded as smoke regions unless M frames of them are classified as smoke ones. Experiment results showed that the proposed method can detect smoke in video effectively and work real-timely.
Face recognition technology is widely applied in daily life, but in most methods, similarity or affine transformation is employed to align face images according to five facial landmarks. The face alignment module is i...
Face recognition technology is widely applied in daily life, but in most methods, similarity or affine transformation is employed to align face images according to five facial landmarks. The face alignment module is implemented independently, thus it's difficult in end-to-end training. In this paper, the main purpose is to design a towards end-to-end trainable face recognition method based on indoor scenes. Due to that spatial transformer can implement any parametrizable transformation, we joint it with recognition network, making end-to-end training possible. Simultaneously, any prior knowledge on facial landmarks isn't required. The model jointly with spatial transformer can achieve 0.3% higher accuracy than similarity transformation. Most downsampling methods ignore the sampling theorem, making convolutional networks not shift-invariant. We replace max-pooling by MaxBlurPool in spatial transformer network, and the accuracy is improved by 0.25%.
Recently, weak value Aw derived in the pre- and post-selected weak measurement has been shown to be powerful in measuring minute physical effects. In principle, the decrease in the post-selection probability will incr...
详细信息
Flexible tissue modeling plays an important role in the field of telemedicine. It is related to whether the soft tissue deformation process can be accurately, real-time and vividly simulated during surgery. However, m...
详细信息
Flexible tissue modeling plays an important role in the field of telemedicine. It is related to whether the soft tissue deformation process can be accurately, real-time and vividly simulated during surgery. Most exist...
详细信息
The memory state feedback control problem for a class of discrete-time systems with input delay and unknown state delay is addressed based on LMIs and Lyapunov-Krasovskii functional method. Under the action of our des...
详细信息
The memory state feedback control problem for a class of discrete-time systems with input delay and unknown state delay is addressed based on LMIs and Lyapunov-Krasovskii functional method. Under the action of our designed adaptive control law, the unknown time-delay parameter is included in memory state feedback controller. Using LMI technique, delay-dependent sufficient conditions for the existence of the feedback controller are obtained. Finally, the effectiveness of the proposed design method is demonstrated by a numerical example.
A brain-computer interface (BCI) establishes a direct communication pathway between the human brain and a computer. It has been widely used in medical diagnosis, rehabilitation, education, entertainment, etc. Most res...
详细信息
This article is aimed at designing a human identity recognition algorithm based on face image, which will be used in indoor environment. As the working environment is set as indoor environment, the camera will not be ...
This article is aimed at designing a human identity recognition algorithm based on face image, which will be used in indoor environment. As the working environment is set as indoor environment, the camera will not be affected much by illumination variation. The key is how to detect human face and handle the variation of facial pose. This article divides the whole recognition process into 4 parts: image pre-processing, face detection, face alignment, feature extraction and comparison. Face detection and feature extraction are the core functions and both realized by deep learning. The process of the whole algorithm can be described as following: images after pre-processing are fed to face detection network to get the locations of face and face landmarks. Then face alignment will be conducted. Finally, deep features of face will be extracted and compared. The unique features of this algorithm are its good performance of handling the variation of facial pose and its clear framework which allows the whole method can be easily adjusted and upgraded.
The technology of the detection for vehicle and driver is a popular spot in these ten years. In particular, the driver detection is still a troubled question in the study of public security. In our paper, an algorithm...
The technology of the detection for vehicle and driver is a popular spot in these ten years. In particular, the driver detection is still a troubled question in the study of public security. In our paper, an algorithm based on YOLOv3 and support vector machine (SVM) is proposed for realizing the detection of vehicles on highway, as well as the detection and binary classification of people in the vehicles, so as to achieve the purpose of distinguishing drivers and passengers and form a one-to-one correspondence between vehicles and drivers. The effectiveness of the algorithm is verified under various complicated highway conditions. Compared with other advanced vehicle and driver detection technologies, the model has a good performance and is robust to road blocking, different attitudes and extreme lighting.
暂无评论