Video surveillance image enhancement via a convolutional neural network and stacked denoising autoencoder

Aminudin, Muhamad Faris Che; Suandi, Shahrel Azmin

doi:10.1007/s00521-021-06551-0

Cited by 11 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this model struggles to capture facial details within highly dark regions of the image and can create blocking artifacts due to heavy compression. Che Aminudin and Suandi [23] proposed a deep learning model that utilizes CNN and an autoencoder model to tackle issues of low illumination, low resolution, and noise. Anitha and Kumar [24] focused on improving image resolution and illumination while reducing noise using a GAN model.…”

Section: Related Workmentioning

confidence: 99%

Augmenting Face Detection in Extremely Low-Light CCTV Footage Using the EDCE Enhancement Model

Sony Priya,

Minu

2023

View full text Add to dashboard Cite

Face detection constitutes a pivotal task in computer vision, with its utility extending across security and surveillance, biometrics, human-computer interaction, and entertainment. This technology facilitates the automated recognition and location of human faces within images or videos, a feature instrumental for identification, authentication, and tracking. However, the efficacy of face detection algorithms is compromised under low-light conditions prevalent in CCTV videos, due to variations in illumination levels. To address this challenge, this study introduces a video enhancement method, the Enhanced Deep Curve Estimation (EDCE), designed to augment the quality of low-light CCTV footage, thereby improving face detection accuracy. To circumvent the redundancy of frames during face detection from the input video, a key frame extraction method was employed. Subsequently, the Retina Face was utilized to detect faces from the enhanced CCTV video keyframes. The CCTV videos evaluated in this study were sourced from public cameras, and the performance of the EDCE model was assessed against other existing enhancement models. The findings reveal that the EDCE model exhibits superior performance with a Peak Signalto-Noise Ratio (PSNR) of 21.37 and a Structural Similarity Index Measure (SSIM) of 0.83. Further, the face detection evaluation yielded an Average Precision of 0.847, signifying the effectiveness of our enhancement methodology. This study, thus, underscores the potential of the EDCE model in enhancing the performance of face detection systems under challenging low-light conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Augmenting Face Detection in Extremely Low-Light CCTV Footage Using the EDCE Enhancement Model

Sony Priya,

Minu

2023

View full text Add to dashboard Cite

show abstract

“…There are various machine learning methods for removing noise in images, including neural networks, deep learning, image recovery methods [1], and regularization methods [2]- [4]. Neural networks [5] and deep learning, such as autoencoding and convolutional neural networks (CNNs) [6], [7] are often used to remove noise in images. In this paper, the methods considered were trained on clean images, and then used this model to remove noise on noisy images.…”

Section: Introductionmentioning

confidence: 99%

Image noise reduction by deep learning methods

Uzakkyzy,

Ismailova,

Ayazbaev

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Image noise reduction is an important task in the field of computer vision and image processing. Traditional noise filtering methods may be limited by their ability to preserve image details. The purpose of this work is to study and apply deep learning methods to reduce noise in images. The main tasks of noise reduction in images are the removal of Gaussian noise, salt and pepper noise, noise of lines and stripes, noise caused by compression, and noise caused by equipment defects. In this paper, such noises as the removal of raindrops, dust, and traces of snow on the images were considered. In the work, complex patterns and high noise density were studied. A deep learning algorithm, such as the decomposition method with and without preprocessing, and their effectiveness in applying noise reduction are considered. It is expected that the results of the study will confirm the effectiveness of deep learning methods in reducing noise in images. This may lead to the development of more accurate and versatile image processing methods capable of preserving details and improving the visual quality of images in various fields, including medicine, photography, and video.</span>

show abstract