Environmental Illumination Conditions Research Articles

Is human perception reliable? Toward illumination robust food freshness prediction from food appearance — Taking lettuce freshness evaluation as an example

Machine vision-based food quality evaluation systems have achieved great attention in industry and academia in recent years because of their high-throughput and non-invasive properties. In practice, the environmental illumination conditions variations would cause visual evaluation bias for both human and machine perceptions. Compared to other existing studies which take sample images and human visual grading under fixed illumination conditions, this study first investigated the environmental illumination effects on the performance of visual-based food grading for both humans and machines. Taking lettuce samples as an example, an image dataset that considered the environmental illumination variations was first established. This dataset encompasses human visual grading scores obtained from sensory panels as well. In contrast to current studies that utilize a single grader or L*a*b* color features to assess sample freshness, our study reveals a substantial impact of environmental illumination on both human perception (p<0.0001) and L*a*b* color features (p<0.0001). In order to enhance the performance of machine vision-based freshness prediction, multitask learning protocols were incorporated into the proposed new network architectures. This allowed the simultaneous prediction of both sample freshness and illumination conditions. In comparison to commonly used generic convolutional neural network models and vision transformer models, the newly proposed model exhibited superior freshness prediction performance. It minimized the prediction error by 20.36%, outperforming the generic ResNet model. This research represents the first quantitative study addressing human and machine perceptions under varied illumination conditions for food quality evaluation. The findings are anticipated to play a pivotal role in expediting the integration of machine vision applications into food engineering practices.

BUILDING CHANGE DETECTION BY W-SHAPE RESUNET++ NETWORK WITH TRIPLE ATTENTION MECHANISM

Abstract. Building change detection in high resolution remote sensing images is one of the most important and applied topics in urban management and urban planning. Different environmental illumination conditions and registration problem are the most error resource in the bitemporal images that will cause pseudochanges in results. On the other hand, the use of deep learning technologies especially convolutional neural networks (CNNs) has been successful and considered, but usually causes the loss of shape and detail at the edges. Accordingly, we propose a W-shape ResUnet++ network in which images with different environmental conditions enter the network independently. ResUnet++ is a network with residual blocks, triple attention blocks and Atrous Spatial Pyramidal Pooling. ResUnet++ is used on both sides of the network to extract deeper and discriminator features. This improves the channel and spatial inter-dependencies, while at the same time reducing the computational cost. After that, the Euclidean distance between the features is computed and the deconvolution is done. Also, a dual loss function is designed that used the weighted binary cross entropy to solve the unbalance between the changed and unchanged data in change detection training data and in the second part, we used the mask–boundary consistency constraints that the condition of converging the edges of the training data and the predicted edge in the loss function has been added. We implemented the proposed method on two remote sensing datasets and then compared the results with state-of-the-art methods. The F1 score improved 1.52 % and 4.22 % by using the proposed model in the first and second dataset, respectively.

Non-uniform illumination image enhancement for surface damage detection of wind turbine blades

Vision-based monitoring technology has been exploited for the surface damage detection of wind turbine blades (WTBs). However, the image quality is often significantly influenced by environmental illumination conditions, imposing difficulties for obtaining high detection accuracy for large-scale WTB surfaces. To improve the image quality and guarantee reliable damage detection on WTB surfaces, this study presents an image processing method for enhancing the images captured under non-uniform illumination conditions. First, cartoon and texture maps of the WTB images are constructed by cartoon texture decomposition. Second, an illumination model is established on the cartoon map from the Gaussian scale-space, to remove the non-uniform illumination. Third, the WTB images are enhanced by utilizing a multi-directional Gabor transformation to increase the contrast between the surface damage and image background. Finally, the WTB surface damages are detected using a gradient threshold segmentation method. The experimental results indicate that the damage detection accuracy of the WTB surfaces is significantly improved by using image enhancement. The F-measure and the intersection-over-union values of the damage detection are increased by 28.05% and 41.61%, respectively, relative to those detected from the input images. Therefore, this vision-based detection method for WTB surface damage inspection under non-uniform illumination has potential application values in practice.

Mobile Phone Operations using Human Eyes Only and its Applications

Mobile phone operations using human eyes only is proposed together with its applications for cooking with referring to recipes and manufacturing with referring to manuals, production procedure, so on. It is found that most of mobile phone operations can be done without touching the screen of the mobile phone. Also, mobile phone operation success rate based on the proposed method is evaluated for the environmental illumination conditions, visible or near infrared (NIR) cameras, the distance between user and mobile phone, as well as pupil size detection accuracy against the environmental illumination changes. Meanwhile, the functionality of two typical applications of the proposed method is confirmed successfully.

Smartphone-Based Point-of-Care Urinalysis Under Variable Illumination.

Urine tests are performed by using an off-the-shelf reference sheet to compare the color of test strips. However, the tabular representation is difficult to use and more prone to visual errors, especially when the reference color-swatches to be compared are spatially apart. Thus, making it is difficult to distinguish between the subtle differences of shades on the reagent pads. This manuscript represents a new arrangement of reference arrays for urine test strips (urinalysis). Reference color swatches are grouped in a doughnut chart, surrounding each reagent pad on the strip. The urine test can be evaluated using naked eye by referring to the strip with no additional sheet necessary. Along with this new strip, an algorithm for smartphone based application is also proposed as an alternative to deliver diagnostic results. The proposed colorimetric detection method evaluates the captured image of the strip, under various color spaces and evaluates ten different tests for urine. Thus, the proposed system can deliver results on the spot using both naked eye and smartphone. The proposed scheme delivered accurate results under various environmental illumination conditions without any calibration requirements, exhibiting performances suitable for real-life applications and an ease for a common user.

Early appearance of nonvisual and circadian markers in the developing inner retinal cells of chicken.

The retina is a key component of the vertebrate circadian system; it is responsible for detecting and transmitting the environmental illumination conditions (day/night cycles) to the brain that synchronize the circadian clock located in the suprachiasmatic nucleus (SCN). For this, retinal ganglion cells (RGCs) project to the SCN and other nonvisual areas. In the chicken, intrinsically photosensitive RGCs (ipRGCs) expressing the photopigment melanopsin (Opn4) transmit photic information and regulate diverse nonvisual tasks. In nonmammalian vertebrates, two genes encode Opn4: the Xenopus (Opn4x) and the mammalian (Opn4m) orthologs. RGCs express both Opn4 genes but are not the only inner retinal cells expressing Opn4x: horizontal cells (HCs) also do so. Here, we further characterize primary cultures of both populations of inner retinal cells (RGCs and HCs) expressing Opn4x. The expression of this nonvisual photopigment, as well as that for different circadian markers such as the clock genes Bmal1, Clock, Per2, and Cry1, and the key melatonin synthesizing enzyme, arylalkylamine N-acetyltransferase (AA-NAT), appears very early in development in both cell populations. The results clearly suggest that nonvisual Opn4 photoreceptors and endogenous clocks converge all together in these inner retinal cells at early developmental stages.

Fast Facial Detection by Depth Map Analysis

In order to obtain correct facial recognition results, one needs to adopt appropriate facial detection techniques. Moreover, the effects of facial detection are usually affected by the environmental conditions such as background, illumination, and complexity of objectives. In this paper, the proposed facial detection scheme, which is based on depth map analysis, aims to improve the effectiveness of facial detection and recognition under different environmental illumination conditions. The proposed procedures consist of scene depth determination, outline analysis, Haar-like classification, and related image processing operations. Since infrared light sources can be used to increase dark visibility, the active infrared visual images captured by a structured light sensory device such as Kinect will be less influenced by environmental lights. It benefits the accuracy of the facial detection. Therefore, the proposed system will detect the objective human and face firstly and obtain the relative position by structured light analysis. Next, the face can be determined by image processing operations. From the experimental results, it demonstrates that the proposed scheme not only improves facial detection under varying light conditions but also benefits facial recognition.

3-D relative positioning sensor for indoor flying robots

Swarms of indoor flying robots are promising for many applications, including searching tasks in collapsing buildings, or mobile surveillance and monitoring tasks in complex man-made structures. For tasks that employ several flying robots, spatial-coordination between robots is essential for achieving collective operation. However, there is a lack of on-board sensors capable of sensing the highly-dynamic 3-D trajectories required for spatial-coordination of small indoor flying robots. Existing sensing methods typically utilise complex SLAM based approaches, or absolute positioning obtained from off-board tracking sensors, which is not practical for real-world operation. This paper presents an adaptable, embedded infrared based 3-D relative positioning sensor that also operates as a proximity sensor, which is designed to enable inter-robot spatial-coordination and goal-directed flight. This practical approach is robust to varying indoor environmental illumination conditions and is computationally simple.