High Dynamic Range Imaging Method Research Articles

Uncertainty estimation in HDR imaging with Bayesian neural networks

The goal of high dynamic range (HDR) imaging is to estimate potential high-quality images from multi-exposed low dynamic range (LDR) inputs. Intuitively, there exist various possible HDR images corresponding to given LDR inputs, which results in uncertainty in the estimated results. However, most existing HDR imaging methods employ l1 or l2 loss only to provide one possible estimation from various possible solutions, which fails to model the uncertainty, and thus lacks high-frequency details. In this work, we design Bayesian neural networks to capture the uncertainty, which can model one-to-many relations and provide various possible solutions. Concretely, we propose a Variational Bayesian Layer by leveraging a hierarchical prior on the network weights and inferring a new joint posterior, which is utilized to model uncertainty in high-frequency details (e.g., textures), and model uncertainty in semantic information (e.g., ghost areas), respectively. By leveraging Bayesian framework, the proposed method can provide various potential high-quality estimations, especially in high-frequency details. Experiments on different datasets show that the proposed method enables sampling possible HDR imaging, and the consensus estimate achieves state-of-the-art quantitative and qualitative results.

Pixel-wise exposure control for single-shot HDR imaging: A joint optimization approach

Dynamic range is one of the primary limitations that restricts digital image sensors from acquiring more visual information. Current high dynamic range (HDR) imaging techniques entail a trade-off between dynamic range and visual fidelity. In this work, we propose a HDR imaging method, termed PE-HDR, to achieve both a wide dynamic range and high visual fidelity without additional complex post-processing algorithms. Instead of merging a bracketed exposure sequence, the PE-HDR captures HDR images in a single shot using optical coded pixel-wise exposure control, enabling cost-effective and flexible HDR imaging. By incorporating a differentiable optical encoder and a neural network decoder, we jointly optimize the imaging pipeline from light irradiance to digital image signals, thereby refining the pixel-wise exposure control strategy and improving image fidelity. Both simulations and experiments demonstrate that the proposed method achieves a dynamic range of up to 120 dB and an excellent visual fidelity with spatial resolution of up to 2560 × 1600 pixels.

Deep progressive feature aggregation network for multi-frame high dynamic range imaging

High dynamic range (HDR) imaging is an important task in image processing that aims to generate well-exposed images in scenes with varying illumination. Although existing multi-exposure fusion methods have achieved impressive results, generating high-quality HDR images in dynamic scenes remains difficult. The primary challenges are ghosting artifacts caused by object motion between low dynamic range images and distorted content in underexposure and overexposed regions. In this paper, we propose a deep progressive feature aggregation network for improving HDR imaging quality in dynamic scenes. To address the issues of object motion, our method implicitly samples high-correspondence features and aggregates them in a coarse-to-fine manner for alignment. In addition, our method adopts a densely connected network structure based on the discrete wavelet transform, which aims to decompose the input features into multiple frequency subbands and adaptively restore corrupted contents. Experiments show that our proposed method can achieve state-of-the-art performance under different scenes, compared to other promising HDR imaging methods. Specifically, the HDR images generated by our method contain cleaner and more detailed content, with fewer distortions, leading to better visual quality.

Research on Belt Deviation Fault Detection Technology of Belt Conveyors Based on Machine Vision

Traditional belt deflection detection devices for underground belt conveyors in coal mines have problems, such as their single function, poor fault location and analysis accuracy, low automation level, and low reliability. In order to solve the defects of traditional detection devices, the belt deviation faults of the underground belt conveyor transport process require to be detected effectively and reliably. This paper proposes a belt deviation detection method based on machine vision. This method makes use of a global adaptive high dynamic range imaging method to complete the brightness enhancement processing of the underground image. Then the straight-line features of the conveyor belt edges are extracted using Canny edge detection and the Hough transform algorithm. In addition, a dual-baseline localization judgment method is proposed to realize the identification of band bias faults. Finally, a test bench for belt conveyor deviation was built. Testing experiments for different deviations were conducted. The accuracy of the tape deviation detection reached 99.45%. The method proposed in this study improves the reliability of belt deviation fault detection of underground belt conveyors in coal mines and has wide application prospects in the field of coal mining.

Improving Endoscopic Image Quality through the Use of High Dynamic Range Imaging-Like Method with Real-Time Performance.

High Dynamic Range (HDR) imaging is a digital image processing technique used to produce a wider range of brightness and color by using multiple captures of a scene taken with different exposures times. It enables capturing more details and producing a more natural-looking image with less washed-out highlights and deeper, more saturated colors. In medical endoscopy, HDR imaging enhances the visibility and clarity of images captured during endoscopy procedures. It provides enhanced visualization of subtler details in both dark cavities and bright areas, resulting in a uniformly exposed view and improved contrast among various tissue types. Standard HDR imaging methods are often complex and computationally demanding, making them unsuitable for performance-critical applications like endoscopy, where real-time performance is crucial. This paper introduces a more efficient and less complex method for achieving HDR-like image quality in real time. The method takes a high-pixel-bit-depth frame and generates multiple low-pixel-bit-depth frames and uses them to generate the high quality image. The focus of the paper is to enhance endoscopic image quality using HDR imaging, and the proposed method is demonstrated to be effective in achieving this goal with real-time performance. The method is implemented in the FPGA System-on-a-Chip (SoC) of a bronchoscope video processor system, and its effectiveness is verified through a simulated study using a phantom, which confirms the improved image quality and real-time performance.

A High Dynamic Range Imaging Method for Short Exposure Multiview Images

The restoration and enhancement of multiview low dynamic range (MVLDR) images captured in low lighting conditions is a great challenge. The disparity maps are hardly reliable in practical, real-world scenarios and suffers from holes and artifacts due to large baseline and angle deviation among multiple cameras in low lighting conditions. Furthermore, multiple images with some additional information (e.g., ISO/exposure time, etc.) are required for the radiance map and poses the additional challenges of deghosting to encounter motion artifacts. In this paper, we proposed a method to reconstruct multiview high dynamic range (MVHDR) images from MVLDR images without relying on disparity maps. We detect and accurately match the feature points among the involved input views and gather the brightness information from the neighboring viewpoints to optimize an image restoration function based on input exposure gain to finally generate MVHDR images. Our method is very reliable and suitable for a wide baseline among sparse cameras. The proposed method requires only one image per viewpoint without any additional information and outperforms others.

High Dynamic Range Imaging Method Based on YCbCr Color Space Fusion

High Dynamic Range Imaging Method Based on YCbCr Color Space Fusion

Enhanced Road Lane Detection Facing Sun Glare

There are several studies on road lane detection but very few address adverse conditions for acquisition such as sun glare. Loss of details in underexposed images captured facing a low sun leads to misleading road lane detection. High Dynamic Range Imaging methods are used to acquire most details in such scenes. Unfortunately, these techniques are heavy on computations and therefore unsuitable for real time road lane detection. In this paper, we propose a machine learning solution that avoids High Dynamic Range Imaging computations that are the radiance map estimation, tone-mapping algorithms and quality measures calculation. We train a neural network on a High Dynamic Range Imaging dataset. The resulting model produces suitable images for road lane detection facing sun glare, in real time. Subjective and objective comparisons with the most popular High Dynamic Range Imaging method, Mertens Algorithm, are conducted to prove the effectiveness of the proposed Neural Network. The delivered images demonstrated an improvement in road lane detection.

MIEHDR CNN: Main Image Enhancement based Ghost-Free High Dynamic Range Imaging using Dual-Lens Systems

We study the High Dynamic Range (HDR) imaging problem using two Low Dynamic Range (LDR) images that are shot from dual-lens systems in a single shot time with different exposures. In most of the related HDR imaging methods, the problem is usually solved by Multiple Images Merging, i.e. the final HDR image is fused from pixels of all the input LDR images. However, ghost artifacts can be hardly avoided using this strategy. Instead of directly merging the multiple LDR inputs, we use an indirect way which enhances the main image, i.e. the short exposure image IS, using the long exposure image IL serving as guidance. In detail, we propose a new model, named MIEHDR CNN model, which consists of three subnets, i.e. Soft Warp CNN, 3D Guided Denoising CNN and Fusion CNN. The Soft Warp CNN aligns IL to get the aligned result ILA using the soft exposed result of IS as reference. The 3D Guided Denoising CNN denoises the soft exposed result of IS using ILA as guidance, whose result are fed into the Fusion CNN with IS to get the HDR result. The MIEHDR CNN model is implemented by MindSpore and experimental results show that we can outperform related methods largely and avoid ghost artifacts.

High-precision width measurement method of laser profile sensor

Purpose Although a laser profile sensor (LPS) can be used to measure dimensions, the “shadow region” generally degrades the accuracy and precision of width measurements. The accuracy and precision of such measurements should be improved. Design/methodology/approach In this paper, the authors propose herein a technique that combines high dynamic range (HDR) imaging with logistic fitting. First, a HDR image is composed of several images acquired with different exposure times, which augments the grayscale of the object profile and significantly reduces overexposure. Next, the profile is fit to a logistic function, which provides accurate and precise edge coordinates. Finally, given the edge coordinates, the object width is calculated. Findings To verify the stability of this logistic algorithm, the authors simulate different noise conditions and different degrees of incomplete edge data. In addition, the progressiveness of the algorithm is demonstrated by comparing the results with those of other algorithms and with the height measurement. Furthermore, the suitability of the system is verified experimentally. Research limitations/implications Because of the limitation of the condition of laboratory, in the experimental section, this paper cannot represent perfectly the industrial situation. It makes this section limited in demonstration. Originality/value In this paper, the results show that the measurement accuracy and precision of the width is improved and exceeds that of the height measurement. The proposed HDR imaging method with logistic fitting may be applied to LPS width measurements, which should significantly aid the development of LPSs.

Calculating luminous flux radiated to a camera lens via high dynamic range photogrammetry

A camera-aided method of using high dynamic range photogrammetry was developed to calculate luminous flux radiated to the camera lens from an environment or its subareas, with per-pixel contributions from visible light-emitting sources, objects, and reflective surfaces. A series of equations were derived to calculate the luminous flux with valid sub-divisibility and additivity. A pilot study was first conducted, followed by a laboratory experiment using an integrating sphere to improve and validate this high dynamic range imaging method with a measurement error of 5.6%. This method was then tested in a real office space to estimate ‘visible’ luminous flux arriving at the camera lens simulating a typical view of 30 office users under four different test scenarios (fluorescent vs. LED lighting, with vs. without access to lighting controls). The luminous flux retrieved from each of a total of 120 high dynamic range images was checked with the illuminance measured at the camera lens. This camera-aided method for remote measurement of luminous flux was proven valid and useful for lighting practice and research. Further investigations on this method are necessary to overcome several limitations and issues of the present study.

Reversible data hiding for high dynamic range images using two-dimensional prediction-error histogram of the second time prediction

High dynamic range (HDR) images have become a wide-spread data format in multimedia communication due to its great expressiveness. In this paper, we present an efficient prediction-error histogram (PEH) based reversible data hiding (RDH) method for HDR images. To better exploit the correlation among encoded channels, a novel RDH scheme based on two-dimensional PEH of the second time prediction is designed. Firstly, the prediction-errors are calculated considering the encoding format of HDR images. Secondly, those pixels located in the complex regions are predicted for the second time by referring to the other channels. Thirdly, the two-dimensional PEH is generated to further optimize the embedding performance and maximize the embedding capacity (EC). Finally, an adaptive embedding strategy based on the two-dimensional PEH is employed to reduce the embedding distortion. With the second time prediction and the two-dimensional PEH strategy, our proposed method can greatly exploit the correlations among channels. Experimental results verify that the proposed method can significantly enlarge the embedding capacity and achieves an excellent embedding performance.

Multi-exposure high dynamic range imaging with informative content enhanced network

For High Dynamic Range (HDR) imaging systems, a new multi-exposure HDR imaging method based on Informative Content Enhanced Network (ICEN) is proposed to overcome the disadvantage that the existing deep learning based methods fails to fully exploit the differently exposed Low Dynamic Range (LDR) image contents to recover the details of the under/over-exposed regions. Specifically, the key contents in differently exposed LDR images that contribute to HDR imaging are firstly defined as Informative Contents (ICs). Then, the ICs are enhanced by the proposed Residual Channel Attention Module (RCAM), and then fused to generate HDR image. Furthermore, a generation scheme is designed for constructing HDR image labels and producing a multi-exposure HDR imaging dataset for training the proposed ICEN. The experimental results show that the proposed method is superior to the existing HDR imaging methods in quantitative and qualitative analysis, and can quickly generate high-quality HDR images.

High Dynamic Range Imaging Based on Bidirectional Structural Similarities and Weighted Low-Rank Matrix Completion

High dynamic range (HDR) imaging, aiming to increase the dynamic range of an image by merging multiexposure images, has attracted much attention. Ghosts are often observed in a resultant image, due to camera motion and object motion in the scene. Low-rank matrix completion (LRMC) provides an effective tool to remove ghosts. However, user specification of the included or excluded regions is required. In this paper, we propose a novel HDR imaging method based on bidirectional structural similarities and weighted low-rank matrix completion. In our method, we first propose the bidirectional structural similarities containing forward-projection structural similarity (FPSS) and backward-projection structural similarity (BPSS) to divide each image into four groups: motion region, saturated region in the source image, saturated region in the reference image, and static and unsaturated regions. Then, the weight maps and the motion maps constructed based on FPSS and BPSS are introduced in the weighted LRMC model to reconstruct the background irradiance maps. Experiments are conducted on several challenging image sets with complex scene, and the results show that the proposed method outperforms three current state-of-the-art methods and Photoshop cs6 and is robust to the reference image.

Perceptual brightness-based inverse tone mapping for high dynamic range imaging

This paper proposes a novel high dynamic range imaging method based on inverse tone mapping for generating a high dynamic range image from a single low dynamic range image. With the increasing expectations for image quality, displays providing high dynamic range images have been released. However, although low dynamic range images are currently commonly used, they do not use the high representation capability of high dynamic range displays. Moreover, high dynamic range contents are scarce. Therefore, high dynamic range imaging techniques are gaining attention. The proposed method involves adaptive specular region detection to determine the bright and dark areas for high dynamic range imaging, output mapping range decision to consider perceptual brightness, final mapping-level decision to prevent degradation of perceptual image quality, and inverse pixel mapping for luminance mapping. The simulation results of the proposed method yielded an HDR-VDP-2 quality score of 59.51, which was higher than those of the conventional methods. Furthermore, the execution time of the proposed algorithm was 0.66 s, which had the lowest complexity compared to the conventional methods. For subjective performance evaluation, we analyzed the perceived image quality on the display with the DRIM, which confirmed the superiority of the proposed method over the conventional methods.

High dynamic range imaging method based on image content adaptive matrix completion

High dynamic range (HDR) imaging usually produces ghosting artifacts, while the traditional matrix completion (MC) method may fail to completely remove the ghosts, without considering the motion characteristics of multi-exposure image. To solve this problem, this paper presents a new HDR imaging method based on content adaptive matrix completion of low dynamic range (LDR) image to remove the ghosts of HDR image. Firstly, according to the image luminance and chrominance information, the LDR image motion area is determined. Then, based on the priori information of motion, the regularization constraint intensity is adjusted in MC process to get each LDR image background information. Finally, a fusion strategy related to multiple exposures is proposed while the difference of details in each image area under different exposures is considered. Regular background sequences and cluttered background sequences are used for experiments. The experimental results demonstrate that, compared with the partial sum minimization of singular values-matrix completion method, the proposed method is more real-time and suitable for cluttered background sequences.

An HDR imaging method with DTDI technology for push-broom cameras

Conventionally, high dynamic-range (HDR) imaging is based on taking two or more pictures of the same scene with different exposure. However, due to a high-speed relative motion between the camera and the scene, it is hard for this technique to be applied to push-broom remote sensing cameras. For the sake of HDR imaging in push-broom remote sensing applications, the present paper proposes an innovative method which can generate HDR images without redundant image sensors or optical components. Specifically, this paper adopts an area array CMOS (complementary metal oxide semiconductor) with the digital domain time-delay-integration (DTDI) technology for imaging, instead of adopting more than one row of image sensors, thereby taking more than one picture with different exposure. And then a new HDR image by fusing two original images with a simple algorithm can be achieved. By conducting the experiment, the dynamic range (DR) of the image increases by 26.02 dB. The proposed method is proved to be effective and has potential in other imaging applications where there is a relative motion between the cameras and scenes.

Stereo Vision-Based High Dynamic Range Imaging Using Differently-Exposed Image Pair.

In this paper, a high dynamic range (HDR) imaging method based on the stereo vision system is presented. The proposed method uses differently exposed low dynamic range (LDR) images captured from a stereo camera. The stereo LDR images are first converted to initial stereo HDR images using the inverse camera response function estimated from the LDR images. However, due to the limited dynamic range of the stereo LDR camera, the radiance values in under/over-exposed regions of the initial main-view (MV) HDR image can be lost. To restore these radiance values, the proposed stereo matching and hole-filling algorithms are applied to the stereo HDR images. Specifically, the auxiliary-view (AV) HDR image is warped by using the estimated disparity between initial the stereo HDR images and then effective hole-filling is applied to the warped AV HDR image. To reconstruct the final MV HDR, the warped and hole-filled AV HDR image is fused with the initial MV HDR image using the weight map. The experimental results demonstrate objectively and subjectively that the proposed stereo HDR imaging method provides better performance compared to the conventional method.

A JPEG backward-compatible image coding scheme for high dynamic range images

Recently, the camera industry began the transition from low dynamic range (LDR) images, using the traditional 8 bits per RGB color representation, to high dynamic range (HDR) images, which use higher bit depths to represent each RGB color. The legacy-JPEG (L-JPEG) standard (ISO/IEC 10918) dominates the LDR image coding market, but offers no support for HDR images. To solve this problem, the JPEG committee (ISO/IEC JTC1 SC29 WG1) initiated a new HDR image coding standardization called JPEG XT (ISO/IEC 18477), which provides L-JPEG backward compatibility. In JPEG XT, HDR images are encoded into base-layer and residual-layer codestreams. An input HDR image is tone-mapped to an LDR image, which is compressed by the L-JPEG encoder, and the base-layer codestream is constructed to provide L-JPEG backward compatibility. The residual-layer codestream allows a residual-layer decoder to reconstruct an HDR version of the LDR codestream. In this paper, we propose a new JPEG backward-compatible image coding method for HDR images. We generate the residual data in the discrete cosine transform (DCT) domain, unlike existing JPEG XT profiles that generate their residual images in the spatial domain. The proposed encoder predicts the DCT coefficients of the input HDR image based on those of the L-JPEG-encoded LDR version. Therefore, the inverse DCT process is not required in our encoding structure, which reduces the encoding time. Experimental results using various sample images show the superiority of the proposed method in terms of encoding time and objective and subjective evaluations.

Gaze and discomfort glare, Part 1: Development of a gaze-driven photometry

Discomfort glare is a major challenge for the design of workplaces. The existing metrics for discomfort glare prediction share the limitation that they do not take gaze direction into account. To overcome this limitation, we developed a ‘gaze-driven’ method for discomfort glare assessment. We conducted a series of experiments under simulated office conditions and recorded the participants’ gaze using mobile eye tracking and the luminance distributions using high dynamic range imaging methods. The two methods were then integrated to derive ‘gaze-centred’ luminance measurements in the field of view. The existing ‘fixed-gaze’ and the newly developed ‘gaze-driven’ measurement methods are compared. Our results show that there is a significant difference between the two methods. In this paper, the procedure for integrating the recorded luminance images with the recorded gaze dynamics for obtaining gaze-centred luminance data is described. This gaze-centred luminance data will be compared to the subjective assessment of glare in Part 2 of this study.