The Goal Of The Program You Are Going To Write Is To Classify Stree The goal of the program you are going to write is to classify street signs, specifically stop signs and speed limit signs. You will test your program using four images: speedsign3.jpg (a 40 km/h speed sign), speedsign12.jpg (an 80 km/h speed sign), speedsign4.jpg (a 100 km/h speed sign), and stop4.jpg (a stop sign). You are provided with a program template named classify_sign_template.cpp, which you should modify to perform the classification task. The program's output will be a copy of each input image with the appropriate label indicating the sign type or "no match" if none are identified. The classification process comprises two main steps. The first step involves identifying the type of sign—either stop sign or speed limit sign—using image processing routines such as Canny edge detection, findContours, and approxPolyDP. Specific parameter values are recommended based on given guidelines: for Canny, use canny_thresh and canny_thresh*2 with a kernel size of 3; for findContours, use the mode RETR_EXTERNAL and the method CHAIN_APPROX_NONE; for approxPolyDP, set the epsilon value to contours[i].size() * 0.02. These parameters can be adjusted but are suggested as effective starting points. The second step activates once a speed limit sign is detected. Using the routines getPerspectiveTransform and warpPerspective, along with the templates speed_40.bmp and speed_80.bmp, the program will determine whether the sign indicates a 40 km/h or 80 km/h speed limit. The code should integrate these functions judiciously, applying perspective correction to isolate the sign before classification. The output should include the modified images with labels and the source code, along with the version of OpenCV used for development.
Paper For Above instruction Accurate classification of street signs is crucial for the development of autonomous driving systems and advanced driver-assistance systems (ADAS). These systems rely heavily on computer vision techniques to interpret environmental cues, wherein street sign recognition forms a vital component. The classification task involves recognizing specific signs such as stop signs and speed limit signs, which inform driver behavior and ensure compliance with traffic laws. The challenge lies in developing a robust algorithm that can accurately distinguish various signs under different conditions, including varying lighting, occlusions, and perspectives. The core methodology for this classification hinges on image processing routines available in OpenCV, a widely used computer vision library. The primary steps involve detecting potential signs through edge