From b202eaee259572cf8b627a776a62ce9d59aa50a6 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Mon, 07 Aug 2017 23:57:56 +0000
Subject: [PATCH] Latency fix for RTSP-camera in console-app
---
src/yolo_v2_class.cpp | 40 ++++++++++++++++++++++++++++++++++------
1 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/src/yolo_v2_class.cpp b/src/yolo_v2_class.cpp
index 31f623c..a2fabcd 100644
--- a/src/yolo_v2_class.cpp
+++ b/src/yolo_v2_class.cpp
@@ -29,6 +29,7 @@
image images[FRAMES];
float *avg;
float *predictions[FRAMES];
+ int demo_index;
};
@@ -102,12 +103,21 @@
#endif
}
+YOLODLL_API int Detector::get_net_width() {
+ detector_gpu_t &detector_gpu = *reinterpret_cast<detector_gpu_t *>(detector_gpu_ptr.get());
+ return detector_gpu.net.w;
+}
+YOLODLL_API int Detector::get_net_height() {
+ detector_gpu_t &detector_gpu = *reinterpret_cast<detector_gpu_t *>(detector_gpu_ptr.get());
+ return detector_gpu.net.h;
+}
-YOLODLL_API std::vector<bbox_t> Detector::detect(std::string image_filename, float thresh)
+
+YOLODLL_API std::vector<bbox_t> Detector::detect(std::string image_filename, float thresh, bool use_mean)
{
std::shared_ptr<image_t> image_ptr(new image_t, [](image_t *img) { if (img->data) free(img->data); delete img; });
*image_ptr = load_image(image_filename);
- return detect(*image_ptr, thresh);
+ return detect(*image_ptr, thresh, use_mean);
}
static image load_image_stb(char *filename, int channels)
@@ -154,7 +164,7 @@
}
}
-YOLODLL_API std::vector<bbox_t> Detector::detect(image_t img, float thresh)
+YOLODLL_API std::vector<bbox_t> Detector::detect(image_t img, float thresh, bool use_mean)
{
detector_gpu_t &detector_gpu = *reinterpret_cast<detector_gpu_t *>(detector_gpu_ptr.get());
@@ -174,12 +184,27 @@
im.h = img.h;
im.w = img.w;
- image sized = resize_image(im, net.w, net.h);
+ image sized;
+
+ if (net.w == im.w && net.h == im.h) {
+ sized = make_image(im.w, im.h, im.c);
+ memcpy(sized.data, im.data, im.w*im.h*im.c * sizeof(float));
+ }
+ else
+ sized = resize_image(im, net.w, net.h);
+
layer l = net.layers[net.n - 1];
float *X = sized.data;
- network_predict(net, X);
+ float *prediction = network_predict(net, X);
+
+ if (use_mean) {
+ memcpy(detector_gpu.predictions[detector_gpu.demo_index], prediction, l.outputs * sizeof(float));
+ mean_arrays(detector_gpu.predictions, FRAMES, l.outputs, detector_gpu.avg);
+ l.output = detector_gpu.avg;
+ detector_gpu.demo_index = (detector_gpu.demo_index + 1) % FRAMES;
+ }
get_region_boxes(l, 1, 1, thresh, detector_gpu.probs, detector_gpu.boxes, 0, 0);
if (nms) do_nms_sort(detector_gpu.boxes, detector_gpu.probs, l.w*l.h*l.n, l.classes, nms);
@@ -252,8 +277,11 @@
bool track_id_absent = !std::any_of(cur_bbox_vec.begin(), cur_bbox_vec.end(), [&](bbox_t const& b) { return b.track_id == i.track_id; });
- if (cur_index >= 0 && track_id_absent)
+ if (cur_index >= 0 && track_id_absent) {
cur_bbox_vec[cur_index].track_id = i.track_id;
+ cur_bbox_vec[cur_index].w = (cur_bbox_vec[cur_index].w + i.w) / 2;
+ cur_bbox_vec[cur_index].h = (cur_bbox_vec[cur_index].h + i.h) / 2;
+ }
}
}
--
Gitblit v1.10.0