Add tensorflow object detection example

Author: Johnson Su

examples/dnnTensorflowObjectDetection.js

@@ -0,0 +1,83 @@
+const fs = require("fs");
+const path = require("path");
+const classNames = require("./dnnTensorflowObjectDetectionClassNames");
+const { cv, drawBlueRect, runVideoDetection } = require("./utils");
+
+if (!cv.xmodules.dnn) {
+  throw new Error("exiting: opencv4nodejs compiled without dnn module");
+}
+
+// replace with path where you unzipped detection model
+const detectionModelPath = "../data/dnn/tf-detection";
+
+const pbFile = path.resolve(detectionModelPath, "frozen_inference_graph.pb");
+const pbtxtFile = path.resolve(
+  detectionModelPath,
+  "ssd_mobilenet_v2_coco_2018_03_29.pbtxt"
+);
+
+if (!fs.existsSync(pbFile) || !fs.existsSync(pbtxtFile)) {
+  console.log("could not find detection model");
+  console.log(
+    "download the model from: https://github.com/opencv/opencv/wiki/TensorFlow-Object-Detection-API#use-existing-config-file-for-your-model"
+  );
+  throw new Error("exiting");
+}
+
+// set webcam port
+const webcamPort = 0;
+
+// initialize tensorflow darknet model from modelFile
+const net = cv.readNetFromTensorflow(pbFile, pbtxtFile);
+
+const classifyImg = img => {
+  // object detection model works with 300 x 300 images
+  const size = new cv.Size(300, 300);
+  const vec3 = new cv.Vec(0, 0, 0);
+
+  // network accepts blobs as input
+  const inputBlob = cv.blobFromImage(img, 1, size, vec3, true, true);
+  net.setInput(inputBlob);
+
+  console.time("net.forward");
+  // forward pass input through entire network, will return
+  // classification result as 1x1xNxM Mat
+  const outputBlob = net.forward();
+  console.timeEnd("net.forward");
+
+  // get height and width from the image
+  const [imgHeight, imgWidth] = img.sizes;
+  const numRows = outputBlob.sizes.slice(2,3);
+
+  for (let y = 0; y < numRows; y += 1) {
+    const confidence = outputBlob.at([0, 0, y, 2]);
+    if (confidence > 0.5) {
+      const classId = outputBlob.at([0, 0, y, 1]);
+      const className = classNames[classId];
+      const boxX = imgWidth * outputBlob.at([0, 0, y, 3]);
+      const boxY = imgHeight * outputBlob.at([0, 0, y, 4]);
+      const boxWidht = imgWidth * outputBlob.at([0, 0, y, 5]);
+      const boxHeight = imgHeight * outputBlob.at([0, 0, y, 6]);
+      const imgRect = new cv.Rect(boxX, boxY, boxWidht, boxHeight);
+
+      // draw the blue rect for the object
+      drawBlueRect(img, imgRect);
+
+      // put text on the object
+      img.putText(
+        className,
+        new cv.Point(boxX, boxY + 0.1 * imgHeight),
+        cv.FONT_ITALIC,
+        2,
+        {
+          color: new cv.Vec(255, 0, 0),
+          thickness: 2
+        }
+      );
+    }
+  }
+
+  cv.imshow("Temsorflow Object Detection", img);
+};
+
+runVideoDetection(webcamPort, classifyImg);

examples/dnnTensorflowObjectDetectionClassNames.js

@@ -0,0 +1,83 @@
+module.exports = {
+  0: "background",
+  1: "person",
+  2: "bicycle",
+  3: "car",
+  4: "motorcycle",
+  5: "airplane",
+  6: "bus",
+  7: "train",
+  8: "truck",
+  9: "boat",
+  10: "traffic light",
+  11: "fire hydrant",
+  13: "stop sign",
+  14: "parking meter",
+  15: "bench",
+  16: "bird",
+  17: "cat",
+  18: "dog",
+  19: "horse",
+  20: "sheep",
+  21: "cow",
+  22: "elephant",
+  23: "bear",
+  24: "zebra",
+  25: "giraffe",
+  27: "backpack",
+  28: "umbrella",
+  31: "handbag",
+  32: "tie",
+  33: "suitcase",
+  34: "frisbee",
+  35: "skis",
+  36: "snowboard",
+  37: "sports ball",
+  38: "kite",
+  39: "baseball bat",
+  40: "baseball glove",
+  41: "skateboard",
+  42: "surfboard",
+  43: "tennis racket",
+  44: "bottle",
+  46: "wine glass",
+  47: "cup",
+  48: "fork",
+  49: "knife",
+  50: "spoon",
+  51: "bowl",
+  52: "banana",
+  53: "apple",
+  54: "sandwich",
+  55: "orange",
+  56: "broccoli",
+  57: "carrot",
+  58: "hot dog",
+  59: "pizza",
+  60: "donut",
+  61: "cake",
+  62: "chair",
+  63: "couch",
+  64: "potted plant",
+  65: "bed",
+  67: "dining table",
+  70: "toilet",
+  72: "tv",
+  73: "laptop",
+  74: "mouse",
+  75: "remote",
+  76: "keyboard",
+  77: "cell phone",
+  78: "microwave",
+  79: "oven",
+  80: "toaster",
+  81: "sink",
+  82: "refrigerator",
+  84: "book",
+  85: "clock",
+  86: "vase",
+  87: "scissors",
+  88: "teddy bear",
+  89: "hair drier",
+  90: "toothbrush"
+};

examples/utils.js

@@ -8,7 +8,7 @@ const dataPath = path.resolve(__dirname, '../data');
 exports.dataPath = dataPath;
 exports.getDataFilePath = fileName => path.resolve(dataPath, fileName);
 
-exports.grabFrames = (videoFile, delay, onFrame) => {
+const grabFrames = (videoFile, delay, onFrame) => {
   const cap = new cv.VideoCapture(videoFile);
   let done = false;
   const intvl = setInterval(() => {
@@ -28,6 +28,13 @@ exports.grabFrames = (videoFile, delay, onFrame) => {
     }
   }, 0);
 };
+exports.grabFrames = grabFrames;
+
+exports.runVideoDetection = (src, detect) => {
+  grabFrames(src, 1, frame => {
+    detect(frame);
+  });
+};
 
 exports.drawRectAroundBlobs = (binaryImg, dstImg, minPxSize, fixedRectWidth) => {
   const {