Optimization of the PID coefficients for the line-follower mobile robot controller employing genetic algorithm

O b j e c t i v e s. To develop a control system for the movement of a mobile robot along a color-contrast line, as well as to find the values of the coefficients of a proportional-integral-differentiating (PID) controller that allows the robot to move along the line at a given speed.M e t ho d s. To adjust the values of the coefficients of the PID controller, methods of enumeration, automatic tuning and a genetic algorithm are used.Re s u l t s. A software package for tuning the PID controller of the educational mobile robot RoboCake, designed to move along a closed color-contrast line at a given speed, has been developed. The software package consists of a simulation model of the specified robot in the Simulink environment, several virtual traces-polygons and a specialized solver based on the developed genetic algorithm. With the help of the proposed fitness function, a mobile robot control system that satisfies the stated conditions is implemented. Based on the conducted model experiments, the desired values of the parameters of the PID controller are obtained.Co n c l u s i o n. A comparison of the effectiveness of various methods of tuning the PID controller is carried out. The developed software package is designed to solve the practical problem of moving a mobile robot along a color-contrast line at a speed of 1 m/s. The results obtained can be used to study methods of evolutionary tuning of stabilization systems for transport robots, ensuring their movement without overshoot.

FLRT3 Marks Direction-Selective Retinal Ganglion Cells That Project to the Medial Terminal Nucleus

The mammalian retina extracts a multitude of diverse features from the visual scene such as color, contrast, and direction of motion. These features are transmitted separately to the brain by more than 40 different retinal ganglion cell (RGC) subtypes. However, so far only a few genetic markers exist to fully characterize the different RGC subtypes. Here, we present a novel genetic Flrt3-CreERT2 knock-in mouse that labels a small subpopulation of RGCs. Using single-cell injection of fluorescent dyes in Flrt3 positive RGCs, we distinguished four morphological RGC subtypes. Anterograde tracings using a fluorescent Cre-dependent Adeno-associated virus (AAV) revealed that a subgroup of Flrt3 positive RGCs specifically project to the medial terminal nucleus (MTN), which is part of the accessory optic system (AOS) and is essential in driving reflex eye movements for retinal image stabilization. Functional characterization using ex vivo patch-clamp recordings showed that the MTN-projecting Flrt3 RGCs preferentially respond to downward motion in an ON-fashion. These neurons distribute in a regular pattern and most of them are bistratified at the level of the ON and OFF bands of cholinergic starburst amacrine cells where they express the known ON-OFF direction-selective RGC marker CART. Together, our results indicate that MTN-projecting Flrt3 RGCs represent a new functionally homogeneous AOS projecting direction-selective RGC subpopulation.

Human visual gamma for color stimuli: When LGN drive is equalized, red is not special

Strong gamma-band oscillations in primate early visual cortex can be induced by spatially homogeneous, high-contrast stimuli, such as color surfaces. Compared to other hues, particularly strong gamma oscillations have been reported for red stimuli. However, precortical color processing and the resultant strength of input to V1 has often not been fully controlled for. This leaves the possibility that stronger responses to some hues were due to differences in V1 input strength. We presented stimuli that had equal luminance and color contrast levels in a color coordinate system based on color responses of the lateral geniculate nucleus, the main input source for area V1. With these stimuli, we recorded magnetoencephalography in 30 human subjects. We found narrowband color-induced gamma oscillations in early visual cortex, which, contrary to previous reports, did not differ between red and green stimuli of equal L-M cone contrast. Notably, blue stimuli with contrast exclusively on the S cone axis induced very weak gamma responses, as well as smaller event-related fields and poorer change detection performance. The strength of human color gamma responses could be well explained by the strength of thalamic input induced by each hue and does not show a clear red bias when this input strength is properly equalized.

The Development of Three Image Quality Evaluation Metrics Based on a Comprehensive Dataset

In this study, a large scale experiment was carried out to assess the image quality of 2266 images using categorical judgement method by 20 observers. These images were rendered in color contrast, chroma, colorfulness, lightness, and vividness directions. The results were used to derive three No-Reference (NR) Image Quality Estimation Models (IQEMs). The first model was based on color science, (different scales in CIELAB). The second model was a Neural Network model while the third model was a statistics model based on color appearance attributes. Their performances were evaluated using two databases, those developed at Zhejiang University and those available from the public databases in terms of correlation coefficients between the objective and predicted image quality scores.

Deep Learning Approach for Submerged Image Enhancement

Because of underwater pictures application in ocean engineering, ocean research, marine biology, and marine archaeology to name a few, underwater picture enhancement was widely publicized in the last several years. Underwater photos frequently upshot in low contrast, blurred, color distortion, hazy, poor visible images. This is because of light attenuation, absorption, scattering (forward scattering and backward scattering), turbidity, floating particles. As a result, effective underwater picture solution must be developedin order to improve visibility, contrast, and color qualities for greater visual quality and optical attractiveness. Many underwater picture enhancing approaches have been proposed to overcome these challenges; however they all failed to produce accurate results. Hence for this we first undertook a large scale underwater image dataset which is trained by convolution neural network (CNN) and then we have studied and implemented a deep learning approach called very deep super resolution (VDSR) model for improving the color, contrast, and brightness of underwater photos by using different algorithms such as white balance, histogram equalization, and gamma correction respectively. Moreover, our method is compared with the existing method which reveals that our method surpassesthe existing methods Keywords: CNN, gamma correction, histogram equalization, underwater image enhancement, VDSR, white balance

Improving KRN.BGT’s Product Knowledge through the List of FAQs on KRN.BGT’s Instagram Stories Highlights

Established in April 2020 by Budi Santosa, KRN.BGT is a fashion brand from Jogja Painting that produces artistic masks by collaborating with other local artists. KRN.BGT is targeting people aged 20s-30s who like visual arts. Although it has a well-designed Instagram account, they still receive many questions from their customers and potential customers regarding their products through Instagram direct messages and comments. Therefore, I decided to improve KRN.BGT’s product knowledge by creating a list of FAQs of its products on its Instagram Stories Highlights, compiled from the direct messages and comments by applying the theories of good FAQs by Biroscak (2019) and color contrast from Alscher (2019) and Evans (2019). I found three USPs from my observation and survey, namely adjustable, suitable for adults and children, and customizable; and include them into the list of FAQs, so its existing and potential customers know more about its products. Keywords: product knowledge, FAQ, Instagram, Instagram Stories Highlights

Is there magnocellular facilitation of early neural processes underlying visual word recognition? Evidence from masked repetition priming with ERPs

An influential theory in the field of visual object recognition proposes that fast magnocellular (M) information facilitates neural processing of spatially more fine-grained but slower parvocellular (P) information. While written words can be considered as a special type of visual objects, it is unknown whether magnocellular facilitation also plays a role in reading. We used a masked priming paradigm that has been shown to result in neural facilitation in visual word processing and tested whether these facilitating effects are mediated by the magnocellular system. In two experiments, we manipulated the influence of magnocellular and parvocellular systems on visual processing of a contextually predictable target character by contrasting high versus low spatial frequency and luminance versus color contrast, respectively. In addition, unchanged (normal) primes were included in both experiments as a manipulation check. As expected, unchanged primes elicited typical repetition effects in the N1, N250 and P3 components of the ERP in both experiments. In the experiment manipulating spatial contrast, we obtained repetition effects only for the N1 component for both M- and P-biased primes. In the luminance versus color contrast experiment, repetition effects were found in N1 and N250 for both M- and P- biased primes. Furthermore, no interactions were found between M- vs. P-biased prime types and repetition. Together these results indicate that M- and P- information contributes jointly to early neural processes underlying visual word recognition.