Neural Video Compression Algorithm

Knop, Michał; Dobosz, Piotr

doi:10.1007/978-3-319-10662-5_8

Cited by 6 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment we performed proved that key frames were correctly found. The method was improved relatively to existing approaches [17]. In our approach the algorithm did not detect key frames between 41-236, when the foreground object (person) was moved beyond the scene.…”

Section: Resultsmentioning

confidence: 96%

“…Knop et al [17] proposed a method based on entropy to determine the complexity of information stored in each frame. The general formula for the entropy on the grayscale video materials is as follows:…”

Section: Entropy Methodsmentioning

confidence: 99%

“…The process of matching two consecutive frames is a challenging issue. This problem can be solved in many ways, such as histogram based methods [8] [27], the correlation of images [18] [29] or entropy [17]. However, most algorithms are sensitive to noise and movements of the camera or objects.…”

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

Video Key Frame Detection Based on SURF Algorithm

Grycuk

Knop

Mandal

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper we present a new method for key frame detection. Our approach is based on a well known algorithm: Speeded-Up Robust Features (SURF), which is a crucial step of our method. The frames are compared by a SURF matcher, which allows to count the corresponding keypoints. The proposed method provides better results for professional and high resolution videos. The simulations we conducted proved the effectiveness of our approach. The algorithm requires only one input parameter.

show abstract

Section: Resultsmentioning

confidence: 96%

Section: Entropy Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Video Key Frame Detection Based on SURF Algorithm

Grycuk

Knop

Mandal

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The method proposed by Knop an Dobosz in [9] is based on entropy from theory of information which is used to determine the complexity of information in each frame. For grayscale video material, entropy can be calculated using the formula below:…”

Section: Entropy Methodsmentioning

confidence: 99%

“…It can be done by starting at any random state of the visible units and performing alternating Gibbs sampling for a very long time. One iteration of alternating Gibbs sampling consists of updating all of the hidden units in parallel using Equation (8) followed by updating all of the visible units in parallel using Equation (9).…”

Section: Surf Key Frame Detection Methodsmentioning

confidence: 99%

Video key frame detection based on the restricted Boltzmann machine

Knop¹,

Kapuściński²,

Mleczko³

2015

J. Appl. Math. Comput. Mech.

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper we present a new method for key frame detection. Our approach is based on a well-known algorithm of the Restricted Boltzmann Machine (RBM), which is a pivotal step in our method. The frames are compared to the RBM matcher, which allows one to search for key frame in the video sequence. The Restricted Boltzmann Machine is one of sophisticated types of neural networks, which can process the probability distribution, and is applied to filtering image recognition and modelling. The learning procedure is based on the matrix description of RBM, where the learning samples are grouped into packages, and represented as matrices. Our research confirms a potential usefulness for video key frame detection. The proposed method provides better results for professional and high-resolution videos. The simulations we conducted proved the effectiveness of our approach. The algorithm requires only one input parameter.

show abstract