Can you Find a Face in a HEVC Bitstream?

Alvar, Saeed Ranjbar; Choi, Hyomin; Bajić, Ivan V.

doi:10.1109/icassp.2018.8462654

Cited by 12 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The keyframe of compressed video data was also evaluated in [ 17 , 18 , 19 , 20 ]. The compressed domain data of High-Efficiency Video Coding was also used for object detection in [ 21 , 22 , 23 , 24 ]. However, only special sections based on the coding syntax were decoded.…”

Section: Related Workmentioning

confidence: 99%

Image Classification in JPEG Compression Domain for Malaria Infection Detection

Dong

Pan

2022

J. Imaging

View full text Add to dashboard Cite

Digital images are usually stored in compressed format. However, image classification typically takes decompressed images as inputs rather than compressed images. Therefore, performing image classification directly in the compression domain will eliminate the need for decompression, thus increasing efficiency and decreasing costs. However, there has been very sparse work on image classification in the compression domain. In this paper, we studied the feasibility of classifying images in their JPEG compression domain. We analyzed the underlying mechanisms of JPEG as an example and conducted classification on data from different stages during the compression. The images we used were malaria-infected red blood cells and normal cells. The training data include multiple combinations of DCT coefficients, DC values in both decimal and binary forms, the “scan” segment in both binary and decimal form, and the variable length of the entire bitstream. The result shows that LSTM can successfully classify the image in its compressed form, with accuracies around 80%. If using only coded DC values, we can achieve accuracies higher than 90%. This indicates that images from different classes can still be well separated in their JPEG compressed format. Our simulations demonstrate that the proposed compression domain-processing method can reduce the input data, and eliminate the image decompression step, thereby achieving significant savings on memory and computation time.

show abstract

Section: Related Workmentioning

confidence: 99%

Image Classification in JPEG Compression Domain for Malaria Infection Detection

Dong

Pan

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Toreyin, uses Wavelet and Markov model for smoke detection in MJPEG2000 compressed video [27]. Bombardelli [30].…”

Section: Related Workmentioning

confidence: 99%

Vehicle License Plate Detector in Compressed Domain

Beratoglu

Töreyi̇n

2021

IEEE Access

View full text Add to dashboard Cite

Data compression techniques allow data size to be reduced prior to data transmission and involve decompression upon transfer. This study shows for the first time that license plate (LP) detection can be accomplished without full decompression of the encoded data. Therefore, by determining in advance which images are required for LP recognition, computational costs of the system can be reduced. The proposed approach is realized on High Efficiency Video Coding (HEVC) based compressed video sequences. Two methods are provided that generate images from HEVC attributes. Fully decoded pixel domain images are also generated for comparative purposes from the same encoded data. The YOLO V3 Tiny Object Detector is used in order to detect LPs in the generated images. EnglishLP, a public dataset, is used to interpret the findings in terms of speed and precision and for comparison with previous studies. An additional contribution of the paper is that a new compressed domain LP database has been created and made publicly available, comprising images captured by a commercial license plate recognition system. Using at least two-orders-of-magnitude less amount of data, the proposed compressed domain LP detector achieved similar precision and recall values to those of the state-of-the-art LP detection schemes tested on both datasets. Moreover, the proposed method results in more than 30% saving in inference time. The results suggest that the proposed method can be utilized for rapid video archive searching applications.

show abstract

“…Fisheye distortion models usually involve intrinsic camera parameters 1 and various lens distortion parameters [6]. To avoid making distortions camera-and lens-specific, we adopted a simpler approach.…”

Section: Fisheye-like Distortionmentioning

confidence: 99%

“…For example, on the well-known Face Detection Data Set and Benchmark (FDDB) [8], recent models such as [10,14] reach near 100% true positive rate with very few false positives. However, face detection in other signal domains, such as 360 • images, point clouds [11], or compressed bitstreams [1,2], has been less explored.…”

Section: Introductionmentioning

confidence: 99%

FDDB-360: Face Detection in 360-Degree Fisheye Images

Fu¹,

Alvar²,

Bajić³

et al. 2019

2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)

View full text Add to dashboard Cite

360• cameras offer the possibility to cover a large area, for example an entire room, without using multiple distributed vision sensors. However, geometric distortions introduced by their lenses make computer vision problems more challenging. In this paper we address face detection in 360 • fisheye images. We show how a face detector trained on regular images can be re-trained for this purpose, and we also provide a 360 • fisheye-like version of the popular FDDB face detection dataset, which we call FDDB-360.

show abstract

Can you Find a Face in a HEVC Bitstream?

Cited by 12 publications

References 18 publications

Image Classification in JPEG Compression Domain for Malaria Infection Detection

Image Classification in JPEG Compression Domain for Malaria Infection Detection

Vehicle License Plate Detector in Compressed Domain

FDDB-360: Face Detection in 360-Degree Fisheye Images

Contact Info

Product

Resources

About