Due to the rapid growth of digital videos and the massive increase in video content, there is an urgent need to develop efficient automatic video content analysis mechanisms for different tasks, namely summarization, retrieval, and classification. In all these applications, one needs to identify shot boundary detection. This paper proposes a novel dual-stage approach for cut transition detection that can withstand certain illumination and motion effects. Firstly, we present a deep neural network model using the pre-trained model combined with long short-term memory LSTM network and the euclidean distance metric. Two parallel pre-trained models sharing the same weights extract the spatial features. Then, these features are fed to the LSTM and the euclidean distance metric to classify the frames into specific categories (similar or not similar). To train the model, we generated a new database containing 5000 frame pairs with two labels (similar, dissimilar) for training and 1000 frame pairs for testing from online videos. Secondly, we adopt the segment selection process to predict the shot boundaries. This preprocessing method can help improve the accuracy and speed of the VSBD algorithm. Then, cut transition detection based on the similarity model is conducted to identify the shot boundaries in the candidate segments. Experimental results on standard databases TRECVid 2001, 2007, and RAI show that the proposed approach achieves better detection rates over the state-of-the-art SBD methods in terms of the F1 score criterion.

Wireless capsule endoscopy (WCE) has several benefits over traditional endoscopy such as its portability and ease of usage, particularly for remote internet of things (IoT)-assisted healthcare services. During the WCE procedure, a significant amount of redundant video data is generated, the transmission of which to healthcare centers and gastroenterologists securely for analysis is challenging as well as wastage of several resources including energy, memory, computation, and bandwidth. In addition to this, it is inherently difficult and time consuming for gastroenterologists to analyze this huge volume of gastrointestinal video data for desired contents. To surmount these issues, we propose a secure video summarization framework for outdoor patients going through WCE procedure. In the proposed system, keyframes are extracted using a light-weighted video summarization scheme, making it more suitable for WCE. Next, a cryptosystem is presented for security of extracted keyframes based on 2D Zaslavsky chaotic map. Experimental results validate the performance of the proposed cryptosystem in terms of robustness and high-level security compared to other recent image encryption schemes during dissemination of important keyframes to healthcare centers and gastroenterologists for personalized WCE.

Les technologies utilisées dans les systèmes de transport intelligents varient, allant

de systèmes de gestion basiques

comme les systèmes de gestion des carrefours à

feux, les systèmes de gestion des conteneurs, les panneaux à messages variables,

radars automatiques ou la vidéosurveillance aux applications plus avancées qui

intègrent des données en temps

-

réel avec ret

ours d'informations de nombreuses

sources, comme les informations météorologiques, ...etc.

Cet article donne un

bref

aperçu sur

une

gestion intelligente des carrefours à feux

utilisant des capteurs sans fils

In this article, a novel sensitive encryption scheme to secure the digital images based on the Zaslavsky chaotic map is proposed. We employ the Zaslavsky chaotic map as a pseudo-random generator to produce the key encryption of the proposed image cryptosystem. The cipher structure has been chosen based on permutation-diffusion processes, where we adopt the classic permutation substitution network, which ensures both confusion and diffusion properties for the encrypted image. Our proposed algorithm has high sensitivity in plain image and the secret key. Moreover, the results show that the characteristics of our approach have excellent performance, with high scores (NPRC = 99.61%, UACI = 33.47%, entropy (CipherImage)  8, and correlation coefficient  0). Experimental results have been studied and analyzed in detail with various types of security analysis. These results demonstrate that our proposed cryptosystem has highly satisfactory security performance and can withstand various attacks compared to state-of-the-art methods.