In the multimedia era, a large volume of video data can be recorded during a certain period of time by multiple cameras. Such rapid growth of video data requires both effective and efficient multi-view video summarization techniques. The users can quickly browse and comprehend a large amount of audiovisual data. It is very difficult in real time to manage and access the huge amount of video content handling issues of interview dependencies, significant variations in illumination and presence of many unimportant frames with low activity. In this paper, we propose a local alignment based FASTA approach to summarize the events in multiview videos as a solution of the aforementioned problems. Deep learning framework is used to extract the features to resolve the problem of variations in illumination and to remove fine texture details and detect the objects in a frame. Inter-view dependencies among multiple views of video are then captured via FASTA algorithm through local alignment. Finally, object tracking is applied to extract the frames with low activity. Subjective as well as objective evaluations clearly indicate the effectiveness of the proposed approach. Experiments show that the proposed summarization method successfully reduces the video content while keeping momentous information in the form of events. A computing analysis of the system also shows that it meets the requirement of real-time applications.
28 March 2018 in Multimedia Tools and Applications
In this digital era, events based video summarization has become an emerging topic in the field of computer vision which finds its applications in video data management, highlights of a game, video surveillance, etc. In this work, we propose a novel network-based approach for event summarization. First, the scale-free network is mapped to a neural network, and then dynamics of a complex video are determined by Chiavlo maps of the network. Second, we declare the neurons as hubs that are exceedingly well linked up as opposed to a majority who receive very short connections. Eventually, these hubs assume as the key-figures of the outcomes; then hubs and all its associated neurons counted for the issue summaries. Experiments show that the proposed approach outperforms the previous existing approaches on Precision and F-measure. The computing cost shows that the proposed model meets the criteria for real-time applications.
Bamboos, also known as non-timber forest products (NTFPs) and belonging to the family Poaceae and subfamily Bambusoideae, have a wide range of flowering cycles from 3 to 120 years; hence, it is difficult to identify species. Here, the focus is on supervised machine learning (ML) and deep learning (DL) as a potential automated approach for the identification and classification of commercial bamboo species, with the help of the majority multiclass voting (MajMulVot) algorithm. We created an image dataset of 2000 bamboo instances, followed by a texture dataset prepared using local binary patterns (LBP) and gray-level cooccurrence matrix (GLCM)-based methods. First, we deployed five ML models for the texture datasets, where support vector machine (SVM) shows an accuracy rate of 82.27%. We next deployed five DL-based convolutional neural network (CNN) models for bamboo classification, namely AlexNet, VGG16, ResNet18, VGG19, and GoogleNet, using the transfer learning (TL) approach, where VGG16 prevails, with an accuracy rate of 88.75%. Further, a MajMulVot-based ensemble approach was introduced to improve the classification accuracy of all ML- and DL-based models. The ML-MajMulVot enhanced the accuracy for the texture dataset to 86.96%. In the same way, DL-MajMulVot increased the accuracy to 92.8%. We performed a comparative analysis of all classification models with and without K-fold cross-validation and MajMulVot methods. The proposed findings indicate that even difficult-to-identify species may be identified accurately with adequate image datasets. The suggested technology can also be incorporated into a mobile app to offer farmers effective agricultural methods.