Semantic segmentation sample.

Author: dkurt

modules/core/include/opencv2/core.hpp

@@ -3159,7 +3159,7 @@ class CV_EXPORTS_W Algorithm
 
 struct Param {
     enum { INT=0, BOOLEAN=1, REAL=2, STRING=3, MAT=4, MAT_VECTOR=5, ALGORITHM=6, FLOAT=7,
-           UNSIGNED_INT=8, UINT64=9, UCHAR=11 };
+           UNSIGNED_INT=8, UINT64=9, UCHAR=11, SCALAR=12 };
 };
 
 
@@ -3252,6 +3252,14 @@ template<> struct ParamType<uchar>
     enum { type = Param::UCHAR };
 };
 
+template<> struct ParamType<Scalar>
+{
+    typedef const Scalar& const_param_type;
+    typedef Scalar member_type;
+
+    enum { type = Param::SCALAR };
+};
+
 //! @} core_basic
 
 } //namespace cv

modules/core/src/command_line_parser.cpp

@@ -104,6 +104,12 @@ static void from_str(const String& str, int type, void* dst)
         ss >> *(double*)dst;
     else if( type == Param::STRING )
         *(String*)dst = str;
+    else if( type == Param::SCALAR)
+    {
+        Scalar& scalar = *(Scalar*)dst;
+        for (int i = 0; i < 4 && !ss.eof(); ++i)
+            ss >> scalar[i];
+    }
     else
         CV_Error(Error::StsBadArg, "unknown/unsupported parameter type");
 

samples/dnn/classification_classes_ILSVRC2012.txt renamed to samples/data/dnn/classification_classes_ILSVRC2012.txt

@@ -0,0 +1,20 @@
+Unlabeled
+Road
+Sidewalk
+Building
+Wall
+Fence
+Pole
+TrafficLight
+TrafficSign
+Vegetation
+Terrain
+Sky
+Person
+Rider
+Car
+Truck
+Bus
+Train
+Motorcycle
+Bicycle

samples/data/dnn/enet-classes.txt

@@ -20,7 +20,14 @@
 | GoogLeNet | `1.0` | `224x224` | `104 117 123` | BGR |
 | [SqueezeNet](https://github.com/DeepScale/SqueezeNet) | `1.0` | `227x227` | `0 0 0` | BGR |
 
+### Semantic segmentation
+|    Model | Scale |   Size WxH|   Mean subtraction | Channels order |
+|---------------|-------|-----------|--------------------|-------|
+| [ENet](https://github.com/e-lab/ENet-training) | `0.00392 (1/255)` | `1024x512` | `0 0 0` | RGB |
+| FCN8s | `1.0` | `500x500` | `0 0 0` | BGR |
+
 ## References
 * [Models downloading script](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/download_models.py)
 * [Configuration files adopted for OpenCV](https://github.com/opencv/opencv_extra/tree/master/testdata/dnn)
 * [How to import models from TensorFlow Object Detection API](https://github.com/opencv/opencv/wiki/TensorFlow-Object-Detection-API)
+* [Names of classes from different datasets](https://github.com/opencv/opencv/tree/master/samples/data/dnn)

samples/dnn/object_detection_classes_coco.txt renamed to samples/data/dnn/object_detection_classes_coco.txt

@@ -1,5 +1,4 @@
 #include <fstream>
-#include <iostream>
 #include <sstream>
 
 #include <opencv2/dnn.hpp>
@@ -17,17 +16,17 @@ const char* keys =
     "{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
     "{ classes     | | Optional path to a text file with names of classes. }"
     "{ mean        | | Preprocess input image by subtracting mean values. Mean values should be in BGR order and delimited by spaces. }"
-    "{ scale       |  1 | Preprocess input image by multiplying on a scale factor. }"
-    "{ width       | -1 | Preprocess input image by resizing to a specific width. }"
-    "{ height      | -1 | Preprocess input image by resizing to a specific height. }"
-    "{ rgb         |    | Indicate that model works with RGB input images instead BGR ones. }"
-    "{ backend     |  0 | Choose one of computation backends: "
-                         "0: default C++ backend, "
-                         "1: Halide language (http://halide-lang.org/), "
-                         "2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
-    "{ target      |  0 | Choose one of target computation devices: "
-                         "0: CPU target (by default),"
-                         "1: OpenCL }";
+    "{ scale       | 1 | Preprocess input image by multiplying on a scale factor. }"
+    "{ width       |   | Preprocess input image by resizing to a specific width. }"
+    "{ height      |   | Preprocess input image by resizing to a specific height. }"
+    "{ rgb         |   | Indicate that model works with RGB input images instead BGR ones. }"
+    "{ backend     | 0 | Choose one of computation backends: "
+                        "0: default C++ backend, "
+                        "1: Halide language (http://halide-lang.org/), "
+                        "2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
+    "{ target      | 0 | Choose one of target computation devices: "
+                        "0: CPU target (by default),"
+                        "1: OpenCL }";
 
 using namespace cv;
 using namespace dnn;
@@ -45,7 +44,9 @@ int main(int argc, char** argv)
     }
 
     float scale = parser.get<float>("scale");
+    Scalar mean = parser.get<Scalar>("mean");
     bool swapRB = parser.get<bool>("rgb");
+    CV_Assert(parser.has("width"), parser.has("height"));
     int inpWidth = parser.get<int>("width");
     int inpHeight = parser.get<int>("height");
     String model = parser.get<String>("model");
@@ -54,19 +55,6 @@ int main(int argc, char** argv)
     int backendId = parser.get<int>("backend");
     int targetId = parser.get<int>("target");
 
-    // Parse mean values.
-    Scalar mean;
-    if (parser.has("mean"))
-    {
-        std::istringstream meanStr(parser.get<String>("mean"));
-        std::vector<float> meanValues;
-        float val;
-        while (meanStr >> val)
-            meanValues.push_back(val);
-        CV_Assert(meanValues.size() == 3);
-        mean = Scalar(meanValues[0], meanValues[1], meanValues[2]);
-    }
-
     // Open file with classes names.
     if (parser.has("classes"))
     {

samples/dnn/object_detection_classes_pascal_voc.txt renamed to samples/data/dnn/object_detection_classes_pascal_voc.txt

@@ -1,5 +1,4 @@
 #include <fstream>
-#include <iostream>
 #include <sstream>
 
 #include <opencv2/dnn.hpp>
@@ -54,23 +53,11 @@ int main(int argc, char** argv)
 
     confThreshold = parser.get<float>("thr");
     float scale = parser.get<float>("scale");
+    Scalar mean = parser.get<Scalar>("mean");
     bool swapRB = parser.get<bool>("rgb");
     int inpWidth = parser.get<int>("width");
     int inpHeight = parser.get<int>("height");
 
-    // Parse mean values.
-    Scalar mean;
-    if (parser.has("mean"))
-    {
-        std::istringstream meanStr(parser.get<String>("mean"));
-        std::vector<float> meanValues;
-        float val;
-        while (meanStr >> val)
-            meanValues.push_back(val);
-        CV_Assert(meanValues.size() == 3);
-        mean = Scalar(meanValues[0], meanValues[1], meanValues[2]);
-    }
-
     // Open file with classes names.
     if (parser.has("classes"))
     {