Function main

dependency/densecrf/examples/dense_inference.cpp:54–115

}

int main( int argc, char* argv[]){
	if (argc<4){
		printf("Usage: %s image annotations output\n", argv[0] );
		return 1;
	}
	// Number of labels
	const int M = 21;
	// Load the color image and some crude annotations (which are used in a simple classifier)
	int W, H, GW, GH;
	unsigned char * im = readPPM( argv[1], W, H );
	if (!im){
		printf("Failed to load image!\n");
		return 1;
	}
	unsigned char * anno = readPPM( argv[2], GW, GH );
	if (!anno){
		printf("Failed to load annotations!\n");
		return 1;
	}
	if (W!=GW || H!=GH){
		printf("Annotation size doesn't match image!\n");
		return 1;
	}
	
	/////////// Put your own unary classifier here! ///////////
	MatrixXf unary = computeUnary( getLabeling( anno, W*H, M ), M );
	///////////////////////////////////////////////////////////
	
	// Setup the CRF model
	DenseCRF2D crf(W, H, M);
	// Specify the unary potential as an array of size W*H*(#classes)
	// packing order: x0y0l0 x0y0l1 x0y0l2 .. x1y0l0 x1y0l1 ...
	crf.setUnaryEnergy( unary );
	// add a color independent term (feature = pixel location 0..W-1, 0..H-1)
	// x_stddev = 3
	// y_stddev = 3
	// weight = 3
	crf.addPairwiseGaussian( 3, 3, new PottsCompatibility( 3 ) );
	// add a color dependent term (feature = xyrgb)
	// x_stddev = 60
	// y_stddev = 60
	// r_stddev = g_stddev = b_stddev = 20
	// weight = 10
	crf.addPairwiseBilateral( 80, 80, 13, 13, 13, im, new PottsCompatibility( 10 ) );
	
	// Do map inference
// 	MatrixXf Q = crf.startInference(), t1, t2;
// 	printf("kl = %f\n", crf.klDivergence(Q) );
// 	for( int it=0; it<5; it++ ) {
// 		crf.stepInference( Q, t1, t2 );
// 		printf("kl = %f\n", crf.klDivergence(Q) );
// 	}
// 	VectorXs map = crf.currentMap(Q);
	VectorXs map = crf.map(5);
	// Store the result
	unsigned char *res = colorize( map, W, H );
	writePPM( argv[3], W, H, res );