Deep Learning Tone-Mapping and Demosaicing for Automotive Vision Systems.

High dynamic range (HDR) imaging technology is increasingly being used in automated driving systems (ADS) for improving the safety of traffic participants in scenes with strong differences in illumination. Therefore, a combination of HDR video, that is video with details in all illumination regimes, and (HDR) object perception techniques that can deal with this variety in illumination is highly desirable. Although progress has been made in both HDR imaging solutions and object detection algorithms in the recent years, they have progressed independently of each other. This has led to a situation in which object detection algorithms are typically designed and constantly improved to operate on 8 bit per channel content. This makes these algorithms not ideally suited for use in HDR data processing, which natively encodes to a higher bit-depth (12 bits/16 bits per channel). In this paper, we present and evaluate two novel convolutional neural network (CNN) architectures that intelligently convert high bit depth HDR images into 8-bit images. We attempt to optimize reconstruction quality by focusing on ADS object detection quality. The first research novelty is to jointly perform tone-mapping with demosaicing by additionally successfully suppressing noise and demosaicing artifacts. The first CNN performs tone-mapping with noise suppression on a full-color HDR input, while the second performs joint demosaicing and tone-mapping with noise suppression on a raw HDR input. The focus is to increase the detectability of traffic-related objects in the reconstructed 8-bit content, while ensuring that the realism of the standard dynamic range (SDR) content in diverse conditions is preserved. The second research novelty is that for the first time, to the best of our knowledge, a thorough comparative analysis against the state-of-the-art tone-mapping and demosaicing methods is performed with respect to ADS object detection accuracy on traffic-related content that abounds with diverse challenging (i.e., boundary cases) scenes. The evaluation results show that the two proposed networks have better performance in object detection accuracy and image quality, than both SDR content and content obtained with the state-of-the-art tone-mapping and demosaicing algorithms.

High-Dynamic-Range Tone Mapping in Intelligent Automotive Systems.

Intelligent driver assistance systems are becoming increasingly popular in modern passenger vehicles. A crucial component of intelligent vehicles is the ability to detect vulnerable road users (VRUs) for an early and safe response. However, standard imaging sensors perform poorly in conditions of strong illumination contrast, such as approaching a tunnel or at night, due to their dynamic range limitations. In this paper, we focus on the use of high-dynamic-range (HDR) imaging sensors in vehicle perception systems and the subsequent need for tone mapping of the acquired data into a standard 8-bit representation. To our knowledge, no previous studies have evaluated the impact of tone mapping on object detection performance. We investigate the potential for optimizing HDR tone mapping to achieve a natural image appearance while facilitating object detection of state-of-the-art detectors designed for standard dynamic range (SDR) images. Our proposed approach relies on a lightweight convolutional neural network (CNN) that tone maps HDR video frames into a standard 8-bit representation. We introduce a novel training approach called detection-informed tone mapping (DI-TM) and evaluate its performance with respect to its effectiveness and robustness in various scene conditions, as well as its performance relative to an existing state-of-the-art tone mapping method. The results show that the proposed DI-TM method achieves the best results in terms of detection performance metrics in challenging dynamic range conditions, while both methods perform well in typical, non-challenging conditions. In challenging conditions, our method improves the detection F2 score by 13%. Compared to SDR images, the increase in F2 score is 49%.

Comparative physicochemical analysis of galvanic sludge wastes.

The paper provides the physicochemical analysis of galvanic sludge to determine the presence and concentration of toxic metals. Two sludges sampled from the same factory, but from different technological processes, alkaline galvanic sludge obtained from galvanizing process and acidic sludge generated from the chromium plating process were analyzed. Inductively Coupled Plasma - Optical Emission Spectrometry (ICP-OES) revealed increased concentrations of toxic heavy metal ions Zn2+, Cr3+, Ni2+ and Pb2+ in the sludge from the galvanizing process and Cr3+, Cu2+, Ni2+, Pb2+, Cd2+ and Zn2+ from the chroming process. Moreover, the sludges were further physicochemically characterized by Reflectance Fourier Transform InfraRed Spectrometry (FTIR), Scanning Electron Microscopy with Energy-dispersive X-ray Spectroscopy Analysis (SEM-EDX) and X-ray diffraction (XRD). The results of ICP-OES were corroborated by FTIR. Analysis of FTIR spectra revealed the specific bands indicating the existence of metal oxides in the analyzed sludges, as well as the presence of organic substances, i.e. solvents and surfactants, used in the electroplating process. The analysis was accomplished following international norms and confirmed the increased concentrations of heavy metal ions from both sludges. In line with the regulations of the Environmental Protection Agency (EPA), the results proved the hypothesis that galvanic sludge is hazardous waste.

The Effect of the Color Filter Array Layout Choice on State-of-the-Art Demosaicing.

Interpolation from a Color Filter Array (CFA) is the most common method for obtaining full color image data. Its success relies on the smart combination of a CFA and a demosaicing algorithm. Demosaicing on the one hand has been extensively studied. Algorithmic development in the past 20 years ranges from simple linear interpolation to modern neural-network-based (NN) approaches that encode the prior knowledge of millions of training images to fill in missing data in an inconspicious way. CFA design, on the other hand, is less well studied, although still recognized to strongly impact demosaicing performance. This is because demosaicing algorithms are typically limited to one particular CFA pattern, impeding straightforward CFA comparison. This is starting to change with newer classes of demosaicing that may be considered generic or CFA-agnostic. In this study, by comparing performance of two state-of-the-art generic algorithms, we evaluate the potential of modern CFA-demosaicing. We test the hypothesis that, with the increasing power of NN-based demosaicing, the influence of optimal CFA design on system performance decreases. This hypothesis is supported with the experimental results. Such a finding would herald the possibility of relaxing CFA requirements, providing more freedom in the CFA design choice and producing high-quality cameras.

Evaluation of periodontal status in HIV infected persons in Croatia.

A number of periodontal changes have been associated with human immunodeficiency virus (HIV) infection, however our knowledge of the epidemiology, microbiology, host response and natural history of these conditions remains limited. Therefore, the aim of our study was the assessment of possible differences in periodontal status of HIV infected subjects when compared with healthy controls matched for age, gender and smoking habit in Croatian population. Assessment included measurement of plaque accumulation using approximal plaque index, measurement of gingival inflammation by use of sulcus bleeding index, pocket depth, gingival recession as well as the number of decayed, missing and filled teeth in 25 HIV infected subjects (age range 22-61, X = 40.8 years) in comparison with 25 healthy controls (age range 20-62, X = 40.9 years). Statistical analysis was performed by use of descriptive statistics and Mann-Whitney U test showed significantly increased level of inflammation of the marginal gingiva in HIV infected subjects when compared to the controls (p < 0.002). Significantly increased mean values of periodontal pockets (p < 0.002) and the deepest periodontal pocket (p < 0.003) were also observed when HIV infected subjects were compared to the healthy controls. In HIV infected subjects there was significant increase in the number of decayed, missing and decrease in the number of filled teeth (p < 0.002; p < 0.002; p < 0.009, respectively). The results of this study once again highlight the need for more prevalent periodontal check-ups and treatments in HIV infected subjects.