The Detection of Video Shot Transitions Based on Primary Segments Using the Adaptive Threshold of Colour-Based Histogram Differences and Candidate Segments Using the SURF Feature Descriptor

Abstract

Aim: Advancements in multimedia technology have facilitated the uploading and processing of videos with substantial content. Automated tools and techniques help to manage vast volumes of video content. Video shot segmentation is the basic symmetry step underlying video processing techniques such as video indexing, content-based video retrieval, video summarization, and intelligent surveillance. Video shot boundary detection segments a video into temporal segments called shots and identifies the video frame in which a shot change occurs. The two types of shot transitions are cut and gradual. Illumination changes, camera motion, and fast-moving objects in videos reduce the detection accuracy of cut and gradual transitions. Materials and Methods: In this paper, a novel symmetry shot boundary detection system is proposed to maximize detection accuracy by analysing the transition behaviour of a video, segmenting it initially into primary segments and candidate segments by using the colour feature and the local adaptive threshold of each segment. Thereafter, the cut and gradual transitions are fine-tuned from the candidate segment using Speeded-Up Robust Features (SURF) extracted from the boundary frames to reduce the algorithmic complexity. The proposed symmetry method is evaluated using the TRECVID 2001 video dataset, and the results show an increase in detection accuracy. Result: The F1 score obtained for the detection of cut and gradual transitions is 98.7% and 90.8%, respectively. Conclusions: The proposed symmetry method surpasses recent state-of-the-art SBD methods, demonstrating increased accuracy for both cut and gradual transitions in videos.

Correlation Coefficients and Adaptive Threshold-Based Dissolve Detection in High-Quality Videos

“…Deep fine edge detection operators increase the chances of misclassification and considering only hard edges increases the probability of transition elimination. The analysis in Table 2 shows that the proposed scheme is comparable concerning a precision score of 91.6 with the SURF feature-based approach in [30] while it outperforms in terms of Recall and F1-measure.…”

“…Table 1 shows the results obtained using our technique. The performance of the proposed scheme is compared with other state of artwork techniques based on quantitative analysis concerning the standard TECHVID 2001 dataset and includes Eigenvalue decomposition and Gaussian transition detection method [23], Walsh-Hadamard transforms kernel-based method [24], temporal segmentation method [25], Multimodal visual feature method [26], 3D convolutional network method [27], visual color information [28], Adaptive thresholds and gradual curve point [29] and SURF feature descriptor [30]. The work proposed in [26] obtained multimodal features using frame-based SURF features thus increasing complexity and ignoring the illumination changes.…”

“…Work done in [28] however tracked the illumination variations in the L*a b color space but was unable to cope with tracking due to poor features on account of rotation and scaling. The adaptive threshold estimated in [30] is estimated over the full-length video which affects the generalization ability of the algorithm when videos involve rapid scene changes.…”

“…The feature set was classified using the SVM classifier to obtain an F1-score of 97% over the TRECVid 2001 dataset. The frames were segmented in [17] into primary and candidate segments to analyze the transition behavior in frames. Segmentation was obtained using the color feature and local adaptive threshold of each part or segment.…”