ans = 23×1带有图层的图层数组:1的数据图像输入227×227×3图片2的zerocenter正常化conv1卷积96年11×11×3旋转步[4 4]和填充[0 0 0 0]3‘relu1 ReLU ReLU 4 norm1的横通道正常化横通道正常化与5频道/元素5“pool1”马克斯池3×3马克斯池步(2 - 2)和填充[0 0 0 0]6conv2卷积256 5×5×48步[1]和填充的卷积[2 2 2 2]7‘relu2 ReLU ReLU 8“norm2”横通道正常化横通道规范化5频道每个元素9“pool2”马克斯池3×3马克斯池步(2 - 2)和填充[0 0 0 0]10 conv3卷积384 3×3×256[1]和隆起与进步填充[1 1 1 1]11的relu3 ReLU ReLU 12 conv4卷积384 3×3×192旋转步[1]和填充[1 1 1 1]13的relu4 ReLU ReLU 14 conv5卷积256 3×3×192旋转步[1]和填充[1 1 1 1]15 ' relu5 ReLU ReLU 16“pool5”马克斯池3×3马克斯池步(2 - 2)和填充[0 0 0 0]17 fc6完全Connected 4096 fully connected layer 18 'relu6' ReLU ReLU 19 'drop6' Dropout 50% dropout 20 'fcLane1' Fully Connected 16 fully connected layer 21 'fcLane1Relu' ReLU ReLU 22 'fcLane2' Fully Connected 6 fully connected layer 23 'output' Regression Output mean-squared-error with 'leftLane_a', 'leftLane_b', and 4 other responses

功能[LANEFOUND，LTPTS，RTPTS] =检测_LANE（帧，LANECOEFFMEANS，LANECOEFFSTDS）％从网络输出，计算％图像坐标中的左右车道点。CALTECH％单声道相机模型描述了相机坐标。％＃codegen％持久对象mynet用于加载系列网络对象。％在第一个调用此函数时，构建持久对象并％设置。当函数被称为后续时间时，重复使用相同的对象以呼叫在输入上的预测，从而避免重建和重新加载％网络对象。持久的lanenet;如果是isempty（lanenet）lanenet = coder.loaddeeplearningnetwork（'lanenet.mat'，'lanenet'）;end lanecoeffsnetworkoutput = lanenet.predict（erfute（帧，[2 1 3]））;通过反转归一化步骤Params = LanecoeffsNetworkOutput来恢复原始Coeffs。* LanecoeffStds + Lanecoeffmeans;IsrightLanefound = ABS（参数（6））> 0.5; %c should be more than 0.5 for it to be a right lane isLeftLaneFound = abs(params(3)) > 0.5; vehicleXPoints = 3:30; %meters, ahead of the sensor ltPts = coder.nullcopy(zeros(28,2,'single')); rtPts = coder.nullcopy(zeros(28,2,'single')); if isRightLaneFound && isLeftLaneFound rtBoundary = params(4:6); rt_y = computeBoundaryModel(rtBoundary, vehicleXPoints); ltBoundary = params(1:3); lt_y = computeBoundaryModel(ltBoundary, vehicleXPoints); % Visualize lane boundaries of the ego vehicle tform = get_tformToImage; % map vehicle to image coordinates ltPts = tform.transformPointsInverse([vehicleXPoints', lt_y']); rtPts = tform.transformPointsInverse([vehicleXPoints', rt_y']); laneFound = true; else laneFound = false; end end function yWorld = computeBoundaryModel(model, xWorld) yWorld = polyval(model, xWorld); end function tform = get_tformToImage % Compute extrinsics based on camera setup yaw = 0; pitch = 14; % pitch of the camera in degrees roll = 0; translation = translationVector(yaw, pitch, roll); rotation = rotationMatrix(yaw, pitch, roll); % Construct a camera matrix focalLength = [309.4362, 344.2161]; principalPoint = [318.9034, 257.5352]; Skew = 0; camMatrix = [rotation; translation] * intrinsicMatrix(focalLength, ... Skew, principalPoint); % Turn camMatrix into 2-D homography tform2D = [camMatrix(1,:); camMatrix(2,:); camMatrix(4,:)]; % drop Z tform = projective2d(tform2D); tform = tform.invert(); end function translation = translationVector(yaw, pitch, roll) SensorLocation = [0 0]; Height = 2.1798; % mounting height in meters from the ground rotationMatrix = (... rotZ(yaw)*... % last rotation rotX(90-pitch)*... rotZ(roll)... % first rotation ); % Adjust for the SensorLocation by adding a translation sl = SensorLocation; translationInWorldUnits = [sl(2), sl(1), Height]; translation = translationInWorldUnits*rotationMatrix; end %------------------------------------------------------------------ % Rotation around X-axis function R = rotX(a) a = deg2rad(a); R = [... 1 0 0; 0 cos(a) -sin(a); 0 sin(a) cos(a)]; end %------------------------------------------------------------------ % Rotation around Y-axis function R = rotY(a) a = deg2rad(a); R = [... cos(a) 0 sin(a); 0 1 0; -sin(a) 0 cos(a)]; end %------------------------------------------------------------------ % Rotation around Z-axis function R = rotZ(a) a = deg2rad(a); R = [... cos(a) -sin(a) 0; sin(a) cos(a) 0; 0 0 1]; end %------------------------------------------------------------------ % Given the Yaw, Pitch, and Roll, determine the appropriate Euler % angles and the sequence in which they are applied to % align the camera's coordinate system with the vehicle coordinate % system. The resulting matrix is a Rotation matrix that together % with the Translation vector defines the extrinsic parameters of the camera. function rotation = rotationMatrix(yaw, pitch, roll) rotation = (... rotY(180)*... % last rotation: point Z up rotZ(-90)*... % X-Y swap rotZ(yaw)*... % point the camera forward rotX(90-pitch)*... % "un-pitch" rotZ(roll)... % 1st rotation: "un-roll" ); end function intrinsicMat = intrinsicMatrix(FocalLength, Skew, PrincipalPoint) intrinsicMat = ... [FocalLength(1) , 0 , 0; ... Skew , FocalLength(2) , 0; ... PrincipalPoint(1), PrincipalPoint(2), 1]; end

代码生成成功：要查看报告，请打开（'codegen / lib / detect_lane / html / export.mldatx'）。

。cnn_lanenet0_0_conv4_w.bin .. cnn_lanenet0_0_conv5_b.bin的.gitignore cnn_lanenet0_0_conv5_w.bin DeepLearningNetwork.cu cnn_lanenet0_0_data_offset.bin DeepLearningNetwork.h cnn_lanenet0_0_data_scale.bin DeepLearningNetwork.o cnn_lanenet0_0_fc6_b.bin MWCNNLayerImpl.cu cnn_lanenet0_0_fc6_w.bin MWCNNLayerImpl.hpp cnn_lanenet0_0_fcLane1_b.bin MWCNNLayerImpl.o cnn_lanenet0_0_fcLane1_w.bin MWCudaDimUtility.CU cnn_lanenet0_0_fcLane2_b.bin MWCudaDimUtility.hpp cnn_lanenet0_0_fcLane2_w.bin MWCustomLayerForCuDNN.cpp cnn_lanenet0_0_responseNames.txt MWCustomLayerForCuDNN.hpp codeInfo.mat MWCustomLayerForCuDNN.o codedescriptor.dmr MWElementwiseAffineLayer.cpp compileInfo.mat MWElementwiseAffineLayer.hpp defines.txt MWElementwiseAffineLayer.o detect_lane.a MWElementwiseAffineLayerImpl.cudetect_lane.cu mwelementwiseaffinelayerimpl.hpp detect_lane.h mwelementwiseaffinelayerimpl.o detect_lane.o mwelementwiseaffinelayerimplkernel.cu detect_lane_data.cu mwelementwiseaffinelayerimplkernel.o detect_lane_data.h MWFusedConvReLULayer.cpp detect_lane_data.o MWFusedConvReLULayer.hpp detect_lane_initialize.cu MWFusedConvReLULayer.o detect_lane_initialize.h MWFusedConvReLULayerImpl.cu detect_lane_initialize.o MWFusedConvReLULayerImpl.hpp detect_lane_ref.rsp MWFusedConvReLULayerImpl.o detect_lane_rtw.mk MWKernelHeaders.hpp detect_lane_terminate.cu MWTargetNetworkImpl.cu detect_lane_terminate。ħMWTargetNetworkImpl.hpp detect_lane_terminate.o MWTargetNetworkImpl.o detect_lane_types.h buildInfo.mat例子cnn_api.cpp gpu_codegen_info.mat cnn_api.hpp HTML cnn_api.o接口cnn_lanenet0_0_conv1_b.bin mean.bin cnn_lanenet0_0_conv1_w.bin predict.cu cnn_lanenet0_0_conv2_b.bin predict.h cnn_lanenet0_0_conv2_w.bin predict.o cnn_lanenet0_0_conv3_b.binttw_proj.tmw cnn_lanenet0_0_conv3_w.bin rtwtypes.h cnn_lanenet0_0_0_conv4_b.bin

/ *版权所有2016 MathWorks，Inc. * / #include  #include  #include  #include  #include #include  #include  #include  #include  #include  #include“detect_lane.h”使用命名空间简历;void ReadData（Float *输入，Mat＆Orig，Mat＆IM）{尺寸尺寸（227,227）;调整大小（orig，Im，size，0,0，Inter_linear）;for（int j = 0; j <227 * 227; j ++）{// bgr到rgb输入[2 * 227 * 227 + j] =（浮点）（im.data [j * 3 + 0]）;输入[1 * 227 * 227 + j] =（浮动）（im.data [j * 3 + 1]）;输入[0 * 227 * 227 + j] =（浮动）（im.data [j * 3 + 2]）;void addlane（float pts [28] [2]，mat＆im，nampts）{std :: vector  iArirray;for（int k = 0; k > orig; if (orig.empty()) break; readData(inputBuffer, orig, im); writeData(inputBuffer, orig, 6, means, stds); cudaEventRecord(stop); cudaEventSynchronize(stop); char strbuf[50]; float milliseconds = -1.0; cudaEventElapsedTime(&milliseconds, start, stop); fps = fps*.9+1000.0/milliseconds*.1; sprintf (strbuf, "%.2f FPS", fps); putText(orig, strbuf, Point(200,30), FONT_HERSHEY_DUPLEX, 1, CV_RGB(0,0,0), 2); imshow("Lane detection demo", orig); if( waitKey(50)%256 == 27 ) break; // stop capturing by pressing ESC */ } destroyWindow("Lane detection demo"); free(inputBuffer); free(outputBuffer); return 0; }