Biblio

Facial expression intensity, which quantifies the degree of facial expression, has been proposed. It is calculated based on how much facial feature values change compared to an expressionless face. The estimation has two aspects. One is to classify facial expressions, and the other is to estimate their intensity. However, it is difficult to do them at the same time. There- fore, in this work, the estimation of intensity and the classification of expression are separated. We suggest an explicit method and an implicit method. In the explicit one, a classifier determines which types of expression the inputs are, and each regressor determines its intensity. On the other hand, in the implicit one, we give zero values or non-zero values to regressors for each type of facial expression as ground truth, depending on whether or not an input image is the correct facial expression. We evaluated the two methods and, as a result, found that they are effective for facial expression recognition.

Eddy Current Pulsed Thermography (ECPT) is widely used in Nondestructive Testing (NDT) of metal defects where the defect information is sometimes affected by coil noise and edge noise, therefore, it is necessary to segment the ECPT image sequences to improve the detection effect, that is, segmenting the defect part from the background. At present, the methods widely used in ECPT are mostly based on matrix decomposition theory. In fact, tensor decomposition is a new hotspot in the field of image segmentation and has been widely used in many image segmentation scenes, but it is not a general method in ECPT. This paper analyzes the feasibility of the usage of tensor decomposition in ECPT and designs several experiments on different samples to verify the effects of two popular tensor decomposition algorithms in ECPT. This paper also compares the matrix decomposition methods and the tensor decomposition methods in terms of treatment effect, time cost, detection success rate, etc. Through the experimental results, this paper points out the advantages and disadvantages of tensor decomposition methods in ECPT and analyzes the suitable engineering application scenarios of tensor decomposition in ECPT.

Some of the key challenges in steganography are imperceptibility and resistance to detection of steganalysis algorithms. Zero steganography is an approach to data hiding such that the cover image is not modified. This paper focuses on the generation of stego-key, which is an essential component of this steganographic approach. This approach utilizes DNA sequences and shifting and flipping operations in its binary code representation. Experimental results show that the key generation algorithm has a low cracking probability. The algorithm satisfies the avalanche criterion.

In this paper, a novel DNA based computing method is proposed for encryption of biometric color(face)and gray fingerprint images. In many applications of present scenario, gray and color images are exhibited major role for authenticating identity of an individual. The values of aforementioned images have considered as two separate matrices. The key generation process two level mathematical operations have applied on fingerprint image for generating encryption key. For enhancing security to biometric image, DNA computing has done on the above matrices generating DNA sequence. Further, DNA sequences have scrambled to add complexity to biometric image. Results of blending images, image of DNA computing has shown in experimental section. It is observed that the proposed substitution DNA computing algorithm has shown good resistant against statistical and differential attacks.

Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.

Human action recognition in video is one of the most widely applied topics in the field of image and video processing, with many applications in surveillance (security, sports, etc.), activity detection, video-content-based monitoring, man-machine interaction, and health/disability care. Action recognition is a complex process that faces several challenges such as occlusion, camera movement, viewpoint move, background clutter, and brightness variation. In this study, we propose a novel human action recognition method using convolutional neural networks (CNN) and deep bidirectional LSTM (DB-LSTM) networks, using only raw video frames. First, deep features are extracted from video frames using a pre-trained CNN architecture called ResNet152. The sequential information of the frames is then learned using the DB-LSTM network, where multiple layers are stacked together in both forward and backward passes of DB-LSTM, to increase depth. The evaluation results of the proposed method using PyTorch, compared to the state-of-the-art methods, show a considerable increase in the efficiency of action recognition on the UCF 101 dataset, reaching 95% recognition accuracy. The choice of the CNN architecture, proper tuning of input parameters, and techniques such as data augmentation contribute to the accuracy boost in this study.

Object recognition with the help of outdoor video surveillance cameras is an important task in the context of ensuring the security at enterprises, public places and even private premises. There have long existed systems that allow detecting moving objects in the image sequence from a video surveillance system. Such a system is partially considered in this research. It detects moving objects using a background model, which has certain problems. Due to this some objects are missed or detected falsely. We propose to combine the moving objects detection results with the classification, using a deep neural network. This will allow determining whether a detected object belongs to a certain class, sorting out false detections, discarding the unnecessary ones (sometimes individual classes are unwanted), to divide detected people into the employees in the uniform and all others, etc. The authors perform a network training in the Keras developer-friendly environment that provides for quick building, changing and training of network architectures. The performance of the Keras integration into a video analysis system, using direct Python script execution techniques, is between 6 and 52 ms, while the precision is between 59.1% and 97.2% for different architectures. The integration, made by freezing a selected network architecture with weights, is selected after testing. After that, frozen architecture can be imported into video analysis using the TensorFlow interface for C++. The performance of such type of integration is between 3 and 49 ms. The precision is between 63.4% and 97.8% for different architectures.

Video streams acquired from thermal cameras are proven to be beneficial in diverse number of fields including military, healthcare, law enforcement, and security. Despite the hype, thermal imaging is increasingly affected by poor resolution, where it has expensive optical sensors and inability to attain optical precision. In recent years, deep learning based super-resolution algorithms are developed to enhance the video frame resolution at high accuracy. This paper presents a comparative analysis of super resolution (SR) techniques based on deep neural networks (DNN) that are applied on thermal video dataset. SRCNN, EDSR, Auto-encoder, and SRGAN are also discussed and investigated. Further the results on benchmark thermal datasets including FLIR, OSU thermal pedestrian database and OSU color thermal database are evaluated and analyzed. Based on the experimental results, it is concluded that, SRGAN has delivered a superior performance on thermal frames when compared to other techniques and improvements, which has the ability to provide state-of-the art performance in real time operations.

This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment.

In this paper, we present an improved approach to transfer style for videos based on semantic segmentation. We segment foreground objects and background, and then apply different styles respectively. A fully convolutional neural network is used to perform semantic segmentation. We increase the reliability of the segmentation, and use the information of segmentation and the relationship between foreground objects and background to improve segmentation iteratively. We also use segmentation to improve optical flow, and apply different motion estimation methods between foreground objects and background. This improves the motion boundaries of optical flow, and solves the problems of incorrect and discontinuous segmentation caused by occlusion and shape deformation.

Due to the potential security problem about key management and distribution for the symmetric image encryption schemes, a novel asymmetric image encryption method is proposed in this paper, which is based on the elliptic curve ElGamal (EC-ElGamal) cryptography and chaotic theory. Specifically, the SHA-512 hash is first adopted to generate the initial values of a chaotic system, and a crossover permutation in terms of chaotic index sequence is used to scramble the plain-image. Furthermore, the generated scrambled image is embedded into the elliptic curve for the encrypted by EC-ElGamal which can not only improve the security but also can help solve the key management problems. Finally, the diffusion combined chaos game with DNA sequence is executed to get the cipher image. The experimental analysis and performance comparisons demonstrate that the proposed method has high security, good efficiency, and strong robustness against the chosen-plaintext attack which make it have potential applications for the image secure communications.

In this paper, new image encryption based on singular value decomposition (SVD), fractional discrete cosine transform (FrDCT) and the chaotic system is proposed for the security of medical image. Reliability, vitality, and efficacy of medical image encryption are strengthened by it. The proposed method discusses the benefits of FrDCT over fractional Fourier transform. The key sensitivity of the proposed algorithm for different medical images inspires us to make a platform for other researchers. Theoretical and statistical tests are carried out demonstrating the high-level security of the proposed algorithm.

In recent years, image steganography is being considered as one of the methods to secure the confidentiality of sensitive and private data sent over networks. Conventional image steganography techniques use cover images to hide secret messages. These techniques are susceptible to steganalysis algorithms based on anomaly detection. This paper proposes a new approach to image steganography without using cover images. In addition, it utilizes Deoxyribonucleic Acid (DNA) sequences. DNA sequences are used to generate key and stego-image. Experimental results show that the use of DNA sequences in this technique offer very low cracking probability and the coverless approach contributes to its high embedding capacity.

The objective of this paper was to propose a 5D combined chaotic system used for image encryption by scrambling and DNA encryption. The initial chaotic values were calculated with a set of equations. The chaotic sequences were used for pixel scrambling, bit scrambling, DNA encryption and DNA complementary function. The average of NPCR, UACI and entropy values of the 6 images used for testing were 99.61, 33.51 and 7.997 respectively. The correlation values obtained for the encrypted image were much lower than the corresponding original image. The histogram of the encrypted image was flat. Based on the theoretical results from the tests performed on the proposed system it can be concluded that the system is suited for practical applications, since it offers high security.

Convolutional Neural Networks (CNN) have shown astonishing results in the field of computer vision. This paper proposes a foreground segmentation algorithm based on CNN to tackle the practical challenges in the video surveillance system such as illumination changes, dynamic backgrounds, camouflage, and static foreground object, etc. The network is trained using the input of image sequences with respective ground-truth. The algorithm employs a CNN called VGG-16 to extract features from the input. The extracted feature maps are upsampled using a bilinear interpolation. The upsampled feature mask is passed through a sigmoid function and threshold to get the foreground mask. Binary cross entropy is used as the error function to compare the constructed foreground mask with the ground truth. The proposed algorithm was tested on two standard datasets and showed superior performance as compared to the top-ranked foreground segmentation methods.

As the traffic congestion increases on the transport network, Payable on the road to slower speeds, longer falter times, as a consequence bigger vehicular queuing, it's necessary to introduce smart way to reduce traffic. We are already edging closer to ``smart city-smart travel''. Today, a large number of smart phone applications and connected sat-naves will help get you to your destination in the quickest and easiest manner possible due to real-time data and communication from a host of sources. In present situation, traffic lights are used in each phase. The other way is to use electronic sensors and magnetic coils that detect the congestion frequency and monitor traffic, but found to be more expensive. Hence we propose a traffic control system using image processing techniques like edge detection. The vehicles will be detected using images instead of sensors. The cameras are installed alongside of the road and it will capture image sequence for every 40 seconds. The digital image processing techniques will be applied to analyse and process the image and according to that the traffic signal lights will be controlled.

Training a feed-forward network for the fast neural style transfer of images has proven successful, but the naive extension of processing videos frame by frame is prone to producing flickering results. We propose the first end-to-end network for online video style transfer, which generates temporally coherent stylized video sequences in near realtime. Two key ideas include an efficient network by incorporating short-term coherence, and propagating short-term coherence to long-term, which ensures consistency over a longer period of time. Our network can incorporate different image stylization networks and clearly outperforms the per-frame baseline both qualitatively and quantitatively. Moreover, it can achieve visually comparable coherence to optimization-based video style transfer, but is three orders of magnitude faster.

Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained by enforcing the outputs of consecutive frames to be both well stylized and temporally consistent. More specifically, a hybrid loss is proposed to capitalize on the content information of input frames, the style information of a given style image, and the temporal information of consecutive frames. To calculate the temporal loss during the training stage, a novel two-frame synergic training mechanism is proposed. Compared with directly applying an existing image style transfer method to videos, our proposed method employs the trained network to yield temporally consistent stylized videos which are much more visually pleasant. In contrast to the prior video style transfer method which relies on time-consuming optimization on the fly, our method runs in real time while generating competitive visual results.

We present an object tracking framework which fuses multiple unstable video-based methods and supports automatic tracker initialization and termination. To evaluate our system, we collected a large dataset of hand-annotated 5-minute traffic surveillance videos, which we are releasing to the community. To the best of our knowledge, this is the first publicly available dataset of such long videos, providing a diverse range of real-world object variation, scale change, interaction, different resolutions and illumination conditions. In our comprehensive evaluation using this dataset, we show that our automatic object tracking system often outperforms state-of-the-art trackers, even when these are provided with proper manual initialization. We also demonstrate tracking throughput improvements of 5× or more vs. the competition.

In this paper, we introduce a fast, secure and robust scheme for digital image encryption using chaotic system of Lorenz, 4D hyper-chaotic system and the Secure Hash Algorithm SHA-1. The encryption process consists of three layers: sub-vectors confusion and two-diffusion process. In the first layer we divide the plainimage into sub-vectors then, the position of each one is changed using the chaotic index sequence generated with chaotic attractor of Lorenz, while the diffusion layers use hyper-chaotic system to modify the values of pixels using an XOR operation. The results of security analysis such as statistical tests, differential attacks, key space, key sensitivity, entropy information and the running time are illustrated and compared to recent encryption schemes where the highest security level and speed are improved.

This paper address the problem of shadow detection and removal in traffic vision analysis. Basically, the presence of the shadow in the traffic sequences is imminent, and therefore leads to errors at segmentation stage and often misclassified as an object region or as a moving object. This paper presents a shadow removal method, based on both color and texture features, aiming to contribute to retrieve efficiently the moving objects whose detection are usually under the influence of cast-shadows. Additionally, in order to get a shadow-free foreground segmentation image, a morphology reconstruction algorithm is used to recover the foreground disturbed by shadow removal. Once shadows are detected, an automatic shadow removal model is proposed based on the information retrieved from the histogram shape. Experimental results on a real traffic sequence is presented to test the proposed approach and to validate the algorithm's performance.

We present a new method for mitigating wall return and a new greedy algorithm for detecting stationary targets after wall clutter has been cancelled. Given limited measurements of a stepped-frequency radar signal consisting of both wall and target return, our objective is to detect and localize the potential targets. Modulated Discrete Prolate Spheroidal Sequences (DPSS's) form an efficient basis for sampled bandpass signals. We mitigate the wall clutter efficiently within the compressive measurements through the use of a bandpass modulated DPSS basis. Then, in each step of an iterative algorithm for detecting the target positions, we use a modulated DPSS basis to cancel nearly all of the target return corresponding to previously selected targets. With this basis, we improve upon the target detection sensitivity of a Fourier-based technique.

An abnormal behavior detection algorithm for surveillance is required to correctly identify the targets as being in a normal or chaotic movement. A model is developed here for this purpose. The uniqueness of this algorithm is the use of foreground detection with Gaussian mixture (FGMM) model before passing the video frames to optical flow model using Lucas-Kanade approach. Information of horizontal and vertical displacements and directions associated with each pixel for object of interest is extracted. These features are then fed to feed forward neural network for classification and simulation. The study is being conducted on the real time videos and some synthesized videos. Accuracy of method has been calculated by using the performance parameters for Neural Networks. In comparison of plain optical flow with this model, improved results have been obtained without noise. Classes are correctly identified with an overall performance equal to 3.4e-02 with & error percentage of 2.5.