[ODCv2] Documentation - add output json file when running on a video to darknet

README.md

@@ -135,6 +135,7 @@ On Linux find executable file `./darknet` in the root directory, while on Window
     `darknet.exe detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights -ext_output -dont_show -out result.json < data/train.txt`
 * To process a list of images `data/train.txt` and save results of detection to `result.txt` use:                             
     `darknet.exe detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights -dont_show -ext_output < data/train.txt > result.txt`
+* To process a video and output results to a json file use: `darknet.exe detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights file.mp4 -dont_show -json_file_output results.json`
 * Pseudo-lableing - to process a list of images `data/new_train.txt` and save results of detection in Yolo training format for each image as label `<image_name>.txt` (in this way you can increase the amount of training data) use:
     `darknet.exe detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights -thresh 0.25 -dont_show -save_labels < data/new_train.txt`
 * To calculate anchors: `darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416`

src/coco.c

@@ -370,6 +370,7 @@ void run_coco(int argc, char **argv)
     int cam_index = find_int_arg(argc, argv, "-c", 0);
     int frame_skip = find_int_arg(argc, argv, "-s", 0);
 	int ext_output = find_arg(argc, argv, "-ext_output");
+    char *json_file_output = find_char_arg(argc, argv, "-json_file_output", 0);
 
     if(argc < 4){
         fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
@@ -384,5 +385,5 @@ void run_coco(int argc, char **argv)
     else if(0==strcmp(argv[2], "valid")) validate_coco(cfg, weights);
     else if(0==strcmp(argv[2], "recall")) validate_coco_recall(cfg, weights);
     else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, hier_thresh, cam_index, filename, coco_classes, 80, frame_skip,
-		prefix, out_filename, mjpeg_port, json_port, dont_show, ext_output, 0);
+		prefix, out_filename, mjpeg_port, json_port, dont_show, ext_output, 0, json_file_output);
 }

src/demo.c

@@ -104,7 +104,7 @@ double get_wall_time()
 }
 
 void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int cam_index, const char *filename, char **names, int classes,
-    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in)
+    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in, char *json_file_output)
 {
     letter_box = letter_box_in;
     in_img = det_img = show_img = NULL;
@@ -117,6 +117,15 @@ void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int
     demo_thresh = thresh;
     demo_ext_output = ext_output;
     demo_json_port = json_port;
+    char *json_buf = NULL;
+    FILE* json_file = NULL;
+
+    if (json_file_output) {
+        json_file = fopen(json_file_output, "wb");
+        char *tmp = "[\n";
+        fwrite(tmp, sizeof(char), strlen(tmp), json_file);
+    }
+
     printf("Demo\n");
     net = parse_network_cfg_custom(cfgfile, 1, 1);    // set batch=1
     if(weightfile){
@@ -226,7 +235,17 @@ void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int
                 send_json(local_dets, local_nboxes, l.classes, demo_names, frame_id, demo_json_port, timeout);
             }
 
-            draw_detections_cv_v3(show_img, local_dets, local_nboxes, demo_thresh, demo_names, demo_alphabet, demo_classes, demo_ext_output);
+            if (json_file_output) {
+                if (json_buf) {
+                    char *tmp = ", \n";
+                    fwrite(tmp, sizeof(char), strlen(tmp), json_file);
+                }
+                json_buf = detection_to_json(local_dets, local_nboxes, l.classes, demo_names, frame_id, NULL);
+                fwrite(json_buf, sizeof(char), strlen(json_buf), json_file);
+                free(json_buf);
+            }
+
+            //draw_detections_cv_v3(show_img, local_dets, local_nboxes, demo_thresh, demo_names, demo_alphabet, demo_classes, demo_ext_output);
             free_detections(local_dets, local_nboxes);
 
             printf("\nFPS:%.1f\n", fps);
@@ -297,6 +316,12 @@ void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int
         printf("output_video_writer closed. \n");
     }
 
+    if (json_file_output) {
+        char *tmp = "\n]";
+        fwrite(tmp, sizeof(char), strlen(tmp), json_file);
+        fclose(json_file);
+    }
+
     // free memory
     release_mat(&show_img);
     release_mat(&in_img);
@@ -322,7 +347,7 @@ void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int
 }
 #else
 void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int cam_index, const char *filename, char **names, int classes,
-    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in)
+    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in, char *json_file_output)
 {
     fprintf(stderr, "Demo needs OpenCV for webcam images.\n");
 }

src/demo.h

@@ -6,7 +6,7 @@
 extern "C" {
 #endif
 void demo(char *cfgfile, char *weightfile, float thresh, float hier_thresh, int cam_index, const char *filename, char **names, int classes,
-    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in);
+    int frame_skip, char *prefix, char *out_filename, int mjpeg_port, int json_port, int dont_show, int ext_output, int letter_box_in, char *json_file_output);
 #ifdef __cplusplus
 }
 #endif

src/detector.c

@@ -1426,6 +1426,7 @@ void run_detector(int argc, char **argv)
     int mjpeg_port = find_int_arg(argc, argv, "-mjpeg_port", -1);
     int json_port = find_int_arg(argc, argv, "-json_port", -1);
     char *out_filename = find_char_arg(argc, argv, "-out_filename", 0);
+    char *json_file_output = find_char_arg(argc, argv, "-json_file_output", 0);
     char *outfile = find_char_arg(argc, argv, "-out", 0);
     char *prefix = find_char_arg(argc, argv, "-prefix", 0);
     float thresh = find_float_arg(argc, argv, "-thresh", .25);    // 0.24
@@ -1492,7 +1493,7 @@ void run_detector(int argc, char **argv)
             if (strlen(filename) > 0)
                 if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0;
         demo(cfg, weights, thresh, hier_thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename,
-            mjpeg_port, json_port, dont_show, ext_output, letter_box);
+            mjpeg_port, json_port, dont_show, ext_output, letter_box, json_file_output);
 
         free_list_contents_kvp(options);
         free_list(options);

src/yolo.c

@@ -338,6 +338,7 @@ void run_yolo(int argc, char **argv)
     int cam_index = find_int_arg(argc, argv, "-c", 0);
     int frame_skip = find_int_arg(argc, argv, "-s", 0);
 	int ext_output = find_arg(argc, argv, "-ext_output");
+    char *json_file_output = find_char_arg(argc, argv, "-json_file_output", 0);
     if(argc < 4){
         fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
         return;
@@ -351,5 +352,5 @@ void run_yolo(int argc, char **argv)
     else if(0==strcmp(argv[2], "valid")) validate_yolo(cfg, weights);
     else if(0==strcmp(argv[2], "recall")) validate_yolo_recall(cfg, weights);
     else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, hier_thresh, cam_index, filename, voc_names, 20, frame_skip,
-		prefix, out_filename, mjpeg_port, json_port, dont_show, ext_output, 0);
+		prefix, out_filename, mjpeg_port, json_port, dont_show, ext_output, 0, json_file_output);
 }