交通标志检测和识别

yolo = 
  SeriesNetwork with properties:

         Layers: [58×1 nnet.cnn.layer.Layer]
     InputNames: {'input'}
    OutputNames: {'classoutput'}

convnet = 
  SeriesNetwork with properties:

         Layers: [14×1 nnet.cnn.layer.Layer]
     InputNames: {'imageinput'}
    OutputNames: {'classoutput'}

function [selectedBbox,idx] = tsdr_predict(img,detectorMATFile,recogMATFile)
%#codegen

% Copyright 2017-2024 The MathWorks, Inc.

% resize the image
img_rz = imresize(img,[448,448]);

% Converting into BGR format
img_rz = img_rz(:,:,3:-1:1);
img_rz = im2single(img_rz);

% create a formatted dlarray with 'SSC' format
dlimg_rz = dlarray(img_rz, 'SSC');

%% Traffic Signal Detection 
persistent detectionnet;
if isempty(detectionnet)   
    detectionnet = coder.loadDeepLearningNetwork(detectorMATFile,'Detection');
end

dlpredictions = predict(detectionnet, dlimg_rz, Outputs = 'fc26');

% Extract numeric array from dlarray
predictions = extractdata(dlpredictions);

%% Convert predictions to bounding box attributes
classes = 1;
num = 2;
side = 7;
thresh = 0.2;
[h,w,~] = size(img);


boxes = single(zeros(0,4));    
probs = single(zeros(0,1));    
for i = 0:(side*side)-1
    for n = 0:num-1
        p_index = side*side*classes + i*num + n + 1;
        scale = predictions(p_index);       
        prob = zeros(1,classes+1);
        for j = 0:classes
            class_index = i*classes + 1;
            tempProb = scale*predictions(class_index+j);
            if tempProb > thresh
                
                row = floor(i / side);
                col = mod(i,side);
                
                box_index = side*side*(classes + num) + (i*num + n)*4 + 1;
                bxX = (predictions(box_index + 0) + col) / side;
                bxY = (predictions(box_index + 1) + row) / side;
                
                bxW = (predictions(box_index + 2)^2);
                bxH = (predictions(box_index + 3)^2);
                
                prob(j+1) = tempProb;
                probs = [probs;tempProb];
                                
                boxX = (bxX-bxW/2)*w+1;
                boxY = (bxY-bxH/2)*h+1;
                boxW = bxW*w;
                boxH = bxH*h;
                boxes = [boxes; boxX,boxY,boxW,boxH];
            end
        end
    end
end

%% Run Non-Maximal Suppression on the detected bounding boxess
coder.varsize('selectedBbox',[98, 4],[1 0]);
[selectedBbox,~] = selectStrongestBbox(round(boxes),probs);

%% Recognition

persistent recognitionnet;
if isempty(recognitionnet) 
    recognitionnet = coder.loadDeepLearningNetwork(recogMATFile,'Recognition');
end

idx = zeros(size(selectedBbox,1),1);
inpImg = coder.nullcopy(zeros(48,48,3,size(selectedBbox,1)));
for i = 1:size(selectedBbox,1)
    
    ymin = selectedBbox(i,2);
    ymax = ymin+selectedBbox(i,4);
    xmin = selectedBbox(i,1);
    xmax = xmin+selectedBbox(i,3);

    
    % Resize Image
    inpImg(:,:,:,i) = imresize(img(ymin:ymax,xmin:xmax,:),[48,48]);
end

% Create a formatted dlarray with 'SSCB' format
dlinpImg = dlarray(single(inpImg), 'SSCB');

for i = 1:size(selectedBbox,1)
    output = predict(recognitionnet, dlinpImg(:,:,:,i));
    [~,idx(i)]=max(extractdata(output));
end

Code generation successful: View report

function tsdr_testVideo

% Copyright 2017-2024 The MathWorks, Inc.

% Input video
v = VideoReader('stop.avi');

detectorNet = 'detectorNet.mat';
recognitionNet = 'recognitionNet.mat';

fps = 0;

while hasFrame(v)
    % Take a frame
    picture = readFrame(v);
    picture = imresize(picture,[480,704]);
    % Call MEX function for Traffic Sign Detection and Recognition
    tic;
    [bboxes,clases] = tsdr_predict_mex(picture,detectorNet,recognitionNet);
    newt = toc;
    
    % fps
    fps = .9*fps + .1*(1/newt);
    
    % display
   
    displayDetections(picture,bboxes,clases,fps);
end


end

function displayDetections(im,boundingBoxes,classIndices,fps)
% Function for inserting the detected bounding boxes and recognized classes
% and displaying the result
%
% Inputs :
%
% im            : Input test image
% boundingBoxes : Detected bounding boxes
% classIndices  : Corresponding classes
%

% Traffic Signs (35)
classNames = {'addedLane','slow','dip','speedLimit25','speedLimit35',...
    'speedLimit40','speedLimit45','speedLimit50','speedLimit55',...
    'speedLimit65','speedLimitUrdbl','doNotPass','intersection',...
    'keepRight','laneEnds','merge','noLeftTurn','noRightTurn','stop',...
    'pedestrianCrossing','stopAhead','rampSpeedAdvisory20',...
    'rampSpeedAdvisory45','truckSpeedLimit55','rampSpeedAdvisory50',...
    'turnLeft','rampSpeedAdvisoryUrdbl','turnRight','rightLaneMustTurn',...
    'yield','yieldAhead','school','schoolSpeedLimit25','zoneAhead45',...
    'signalAhead'};

outputImage = insertShape(im,'Rectangle',boundingBoxes,'LineWidth',3);

for i = 1:size(boundingBoxes,1)
    
     ymin = boundingBoxes(i,2);
     xmin = boundingBoxes(i,1);
     xmax = xmin+boundingBoxes(i,3);
    
    % inserting class as text at YOLO detection
    classRec = classNames{classIndices(i)};
    outputImage = insertText(outputImage,[xmax ymin-20],classRec,...
        'FontSize',20,'TextColor','red');
    
end
outputImage = insertText(outputImage,...
    round(([size(outputImage,1) 40]/2)-20),...
    ['Frame Rate: ',num2str(fps)],'FontSize',20,'TextColor','red');
imshow(outputImage);
end