An autonomous vehicle company trains a vision model that assigns every individual pixel in a camera frame to a category such as road, sidewalk, vehicle, or pedestrian, producing a colored map of the entire scene rather than boxes drawn around individual objects. Which computer vision technique is being described?
Select an answer to reveal the explanation.
Short Explanation
The giveaway detail here is that every single pixel gets its own category, not just a box drawn loosely around an object and not one label slapped on the whole picture. That pixel-by-pixel coloring, where the road is one color, the sidewalk another, a pedestrian another, is a distinct technique from drawing rectangles around objects, which only approximates where something is rather than tracing its exact shape. It's also different from labeling an entire frame with a single tag, since that tells you nothing about where the road ends and the sidewalk begins. And reading text off a sign in the frame is an entirely unrelated task focused on characters, not scene regions. The technique that produces a full, detailed, pixel-level map of the scene is the one being described.
Full Explanation
The correct answer is C. Semantic segmentation classifies every individual pixel in an image into a category, producing a dense, per-pixel map of the scene, such as marking which pixels belong to the road, the sidewalk, a vehicle, or a pedestrian, which precisely matches the colored scene map the autonomous vehicle company is generating. Option A is incorrect because object detection locates discrete objects and marks each one with a bounding box around its approximate location, which produces boxes rather than the pixel-by-pixel category map described in the scenario. Option B is incorrect because image classification assigns one overall label to an entire image, such as 'street scene,' and cannot distinguish or label the many different regions within a single frame the way the described model does. Option D is incorrect because optical character recognition extracts and reads printed or handwritten text characters from an image, such as a street sign, which has nothing to do with categorizing every pixel of a scene by object type. Because the scenario explicitly describes pixel-level categorization across the whole frame rather than boxes, a whole-image label, or text extraction, semantic segmentation is the only technique that matches.