Segregation of oil palm fruit ripeness using color sensor

Oil palm is an important industry that has contributed to income and support to the economic sector especially for Malaysia and Indonesia. However, most of the equipment in the oil palm industry is still operated manually. This work developed a system to separate bunches of oil palm fruit using color sensors according to maturity level. Fruit color plays a decisive point in determining fruit maturity. Here, a specific threshold point of red green blue (RGB) was obtained for the determination of the maturity level of oil palm fruit. Point values of < 120, 120 < x < 150 and > 150 represent the maturity levels of unripe, under ripe and ripe, respectively. This paper is the first to report the RGB points for use in the development of automated oil palm segregation system in the oil palm plantation industry. Thus, this paper will pave the way in producing an accurate and reliable oil palm separation system, which in turn has a positive effect in reducing human error. In the future, a set of sensors is proposed to detect a bunch of the oil palm fruits. This further can speed up the segregation process and more suitable for adaptation to the industry.

Multimedia Concepts on Object Detection and Recognition with F1 Car Simulation Using Convolutional Layers

This paper presents a framework for detecting objects in images based on global features and contours. The first step is a shape matching algorithm that uses the background subtraction process. Object detection is accomplished by an examination of the oversegmentation of the image, where the space of the potential boundary of the object is examined to identify boundaries that have a direct resemblance to the prototype of the object type to be detected. Our analysis method removes edges using bilinear interpolation and reestablishes color sensors as lines and retracts background lines from the previous frame. Object contours are generated with clustered lines. The objects detected will then be recognized using the extraction technique. Here, we analyze the color and shape characteristics with which each object is capable of managing occlusion and interference. As an extension of object detection and recognition, F1 car simulation is experimented with simulation using various layers, such as layer drops, convolutionary layers, and boundary elimination, avoiding obstacles in different pathways.

Evaluation of satellite sensors to compute Chlorophyll-a concentration in the Northeastern Arabian Sea: A validation approach

The primary productivity of an aquatic system like the Arabian Sea is broadly determined by the concentration of Chlorophyll-a (Chl-a/Ca) pigment. The present study is essaying to validate the Chl-a data set retrieved from the prominent ocean color sensors (OC3M - MODIS, OC-OCM2, and OC3V-VIIRS) with sea truth data, collected from 204 stations for a three year period (2015–2017). The in-situ concentrations of Chl-a depict the geographic region under the mesotrophic and eutrophic spans with a mean of 1.36 mg m-3 ((0.1 > Ca>1.0 mg m-3). The ratio of CaOCM2/CaIn-situ was 0.97 ± 0.27 mg m-3 (n = 199), but the ratios were higher with CaVIIRS/CaIn-situ is 1.75 ± 0.79 mg m-3 (n = 170) and CaMODIS/CaIn-situ is 2.53 ± 1.42 mg m-3 (n = 158). The coefficient of determination proclaims a moderate significant relationship for MODIS (R2 = 0.36; p < 0.001), followed OCM2 (R2 = 0.32; p < 0.001) and VIIRS (R2 = 0.19; p < 0.001). The OCM2 showed the lowest RMSE as 0.13, which is relatively lower than the reference error limit by global ocean color missions at 0.35. In overall performance among three algorithms, the OCM2 will provide a better estimation of Chl-a with a prediction of 32% accuracy and 34.37 % of bias. The log bias values for MODIS (0.35) and VIIRS (0.20) algorithms indicating the overestimation of Chl-a with in-situ Chl-a, but the OCM2 algorithm is suitable in the region with a negligible bias (-0.03). The biogeochemical processes and ecosystem characteristics are dynamic from region to region, as yet in its urgent need to validate global sensors to fine-tune the regional algorithms periodically.

An Improved Cloud Masking Method for GOCI Data over Turbid Coastal Waters

Clouds severely hinder the radiative transmission of visible light; thus, correctly masking cloudy and non-cloudy pixels is a preliminary step in processing ocean color remote sensing data. However, cloud masking over turbid waters is prone to misjudgment, leading to loss of non-cloudy pixel data. This research proposes an improved cloud masking method over turbid water to classify cloudy and non-cloudy pixels based on spectral variability of Rayleigh-corrected reflectance acquired by the Geostationary Ocean Color Imager (GOCI). Compared with other existing cloud masking methods, we demonstrated that this improved method can identify the spatial positions and shapes of clouds more realistically, and more accurate pixels of turbid waters were retained. This improved method can be effectively applied in typical turbid coastal waters. It has potential to be used in cloud masking procedures of spaceborne ocean color sensors without short-wave infrared bands.

High Spatial-Resolution Red Tide Detection in the Southern Coast of Korea Using U-Net from PlanetScope Imagery

Red tides caused by Margalefidinium polykrikoides occur continuously along the southern coast of Korea, where there are many aquaculture cages, and therefore, prompt monitoring of bloom water is required to prevent considerable damage. Satellite-based ocean-color sensors are widely used for detecting red tide blooms, but their low spatial resolution restricts coastal observations. Contrarily, terrestrial sensors with a high spatial resolution are good candidate sensors, despite the lack of spectral resolution and bands for red tide detection. In this study, we developed a U-Net deep learning model for detecting M. polykrikoides blooms along the southern coast of Korea from PlanetScope imagery with a high spatial resolution of 3 m. The U-Net model was trained with four different datasets that were constructed with randomly or non-randomly chosen patches consisting of different ratios of red tide and non-red tide pixels. The qualitative and quantitative assessments of the conventional red tide index (RTI) and four U-Net models suggest that the U-Net model, which was trained with a dataset of non-randomly chosen patches including non-red tide patches, outperformed RTI in terms of sensitivity, precision, and F-measure level, accounting for an increase of 19.84%, 44.84%, and 28.52%, respectively. The M. polykrikoides map derived from U-Net provides the most reasonable red tide patterns in all water areas. Combining high spatial resolution images and deep learning approaches represents a good solution for the monitoring of red tides over coastal regions.

Automatic Control of Color Sorting and Pick/Place of a 6- DOF Robot Arm

This work focuses on the implementation and design of a six degree of freedom, 6-DOF control of automatic color sorting and pick and place tasks for a robot arm using wireless controlling interface – Blynk apps. Based on the collaboration between the servo motor and input color sensor, this wireless control of automatic color sorting robot arm provides a powerful wireless control GUI (Graphics User Interface) and to enable the method for manual color sorting mode. The color sorting mode is performed once the mode is turned on by the user. The robot arm able to differentiate the colors of the object (input) and categorize or classify the object to the correct places automatically. It provides a stable, efficient, and precision results without any vibration of control as the main target for this project. In this work, six servo motors were used to realize the real robotic arm for industrial use. Five servos were operated to control the entire robot arm motion including the base, shoulder, and elbow as well as one servo is reserved for the positioning of the end effector. Two input variables namely TSC3200 Color Sensors & HC-SR04 Ultrasonic Sensors were employed as the input for the robot arm. The output variable mainly focused on the servo motor as the links for the robot arm to reposition and change the motion for the entire system.

Tackling Heterogeneous Color Registration: Binning Color Sensors

Intelligent systems for interior lighting strive to balance economical, ecological, and health-related needs. For this purpose, they rely on sensors to assess and respond to the current room conditions. With an augmented demand for more dedicated control, the number of sensors used in parallel increases considerably. In this context, the present work focuses on optical sensors with three spectral channels used to capture color-related information of the illumination conditions such as their chromaticities and correlated color temperatures. One major drawback of these devices, in particular with regard to intelligent lighting control, is that even same-type color sensors show production related differences in their color registration. Standard methods for color correction are either impractical for large-scale production or they result in large colorimetric errors. Therefore, this article shows the feasibility of a novel sensor binning approach using the sensor responses to a single white light source for cluster assignment. A cluster specific color correction is shown to significantly reduce the registered color differences for a selection of test stimuli to values in the range of 0.003–0.008 Δu′v′, which enables the wide use of such sensors in practice and, at the same time, requires minimal additional effort in sensor commissioning.