OCTOPAS Project | Monish Saravana

Project Overview

The Problem

Marine oil spills are an environmental catastrophe, with over 15,000 tonnes of crude oil spilled annually. Traditional cleanup methods are slow, manually intensive, and often inefficient, struggling to adapt to the dynamic nature of a spill.

The Solution

OCTOPAS is a two-part system designed to revolutionize oil spill response. It combines a physical autonomous surface vessel (ASV) with a sophisticated computer vision software brain to identify, map, and coordinate cleanup with maximum efficiency.

Technical Deep Dive

Image Acquisition

The system begins with an aerial image of the spill. This image is scaled and converted to the HSV color space to make the oil distinct regardless of lighting.

K-Means Segmentation

Using Scikit-learn, the system clusters pixels to automatically segment the image into "oil" and "water" without manual thresholding.

Path Optimization

OpenCV calculates the convex hull of the oil patch to determine the most efficient path for the containment boom to encircle the spill.

Python / OpenCV / Scikit-learn

class oilSpillImage:
    def findOil(self, img, number=2):
        # Convert image to HSV and normalize
        img = cv.cvtColor(img, cv.COLOR_BGR2HSV) / 255
        h, w, c = img.shape
        img2 = img.reshape(h * w, c)

        # Quantize to N colors using K-Means clustering
        kmeans_cluster = cluster.KMeans(n_clusters=number)
        kmeans_cluster.fit(img2)

        # Reshape image back to original dimensions
        img3 = cluster_centers[cluster_labels].reshape(h, w, c) * 255
        return img3.astype('uint8')

    def makePerimeters(self, real_img, reduced_img):
        # Create a single, unified hull around all detected spills
        all_points = np.vstack(oil_contours)
        unified_hull = cv.convexHull(all_points)

        cv.drawContours(real_img, [unified_hull], -1, (165, 255, 0), 4)
        return real_img

OCTOPAS