From 5c012ed4cccd0efd6cad88a5b7346d1a29176954 Mon Sep 17 00:00:00 2001
From: Vladimir Mandic <mandic00@live.com>
Date: Wed, 17 Mar 2021 11:32:26 -0400
Subject: [PATCH] add experimental nanodet object detection

---
 Configuration.md | 14 ++++++++++++--
 Credits.md       |  1 +
 Models.md        |  2 ++
 Outputs.md       | 12 ++++++++++++
 Usage.md         |  1 +
 5 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/Configuration.md b/Configuration.md
index a0c8f41..17c1db3 100644
--- a/Configuration.md
+++ b/Configuration.md
@@ -154,8 +154,8 @@ config = {
     },
 
     embedding: {
-      enabled: false,        // to improve accuracy of face embedding extraction it is recommended
-                             // to enable detector.rotation and mesh.enabled
+      enabled: false,        // to improve accuracy of face embedding extraction it is
+                             // highly recommended to enable detector.rotation and mesh.enabled
       modelPath: '../models/mobileface.json',
     },
   },
@@ -199,6 +199,16 @@ config = {
       modelPath: '../models/handskeleton.json',
     },
   },
+
+  object: {
+    enabled: false,
+    modelPath: '../models/nanodet.json',
+    minConfidence: 0.15,     // threshold for discarding a prediction
+    iouThreshold: 0.25,      // threshold for deciding whether boxes overlap too much
+                             // in non-maximum suppression
+    maxResults: 10,          // maximum number of objects detected in the input
+    skipFrames: 13,          // how many frames to go without re-running the detector
+  },
 };
 ```
 
diff --git a/Credits.md b/Credits.md
index d2c1077..651283b 100644
--- a/Credits.md
+++ b/Credits.md
@@ -9,6 +9,7 @@
 - Age & Gender Prediction: [**SSR-Net**](https://github.com/shamangary/SSR-Net)
 - Emotion Prediction: [**Oarriaga**](https://github.com/oarriaga/face_classification)
 - Face Embedding: [**BecauseofAI MobileFace**](https://github.com/becauseofAI/MobileFace)
+- ObjectDetection: [**NanoDet**](https://github.com/RangiLyu/nanodet)
 - Image Filters: [**WebGLImageFilter**](https://github.com/phoboslab/WebGLImageFilter)
 - Pinto Model Zoo: [**Pinto**](https://github.com/PINTO0309/PINTO_model_zoo)
 
diff --git a/Models.md b/Models.md
index c7aa3b9..3b32001 100644
--- a/Models.md
+++ b/Models.md
@@ -12,6 +12,7 @@ Default models in Human library are:
 - **Age Detection**: SSR-Net Age IMDB
 - **Body Analysis**: PoseNet
 - **Face Embedding**: BecauseofAI MobileFace Embedding
+- **Object Detection**: NanoDet
 
 ## Notes
 
@@ -50,6 +51,7 @@ Default models in Human library are:
 | Sirius-AI MobileFaceNet | 125K | mobilefacenet.json | 5.0M | mobilefacenet.bin | 139 |
 | BecauseofAI MobileFace | 33K | mobileface.json | 2.1M | mobileface.bin | 75 |
 | FaceBoxes | 212K | faceboxes.json | 2.0M | faceboxes.bin | N/A |
+| NanoDet | 255K | nanodet.json | 1.9M | nanodet.bin | 524 |
 
 <br>
 
diff --git a/Outputs.md b/Outputs.md
index 5590563..593a830 100644
--- a/Outputs.md
+++ b/Outputs.md
@@ -57,6 +57,18 @@ result = {
       annotations, // <array of 3D landmarks [ landmark: <array of points> ]> 5 annotated landmakrs
     }
   ],
+  object:          // <array of detected objects>
+  [
+    {
+      score,       // <number>
+      class,       // <number> class id based on coco labels
+      label,       // <string> class label based on coco labels
+      center,      // [<number>, <number>] x,y coordinates of the object center
+      box,         // [<number>, <number>, <number>, <number>] x1, y1, x2, y2 coordinates of the box around the detected object
+      centerRaw,   // same as center but normalized to range 0..1
+      boxRaw,      // same as box, but normalized to range 0..1
+    }
+  ],
   gesture:         // <array of objects object>
   [
     {
diff --git a/Usage.md b/Usage.md
index 5e02eb2..8901618 100644
--- a/Usage.md
+++ b/Usage.md
@@ -70,6 +70,7 @@ Additional helper functions inside `human.draw`:
   human.draw.face(canvas, results.face)      // draw face detection results to canvas
   human.draw.body(canvas, results.body)      // draw body detection results to canvas
   human.draw.hand(canvas, result.hand)       // draw hand detection results to canvas
+  human.draw.object(canvas, result.object)   // draw object detection results to canvas
   human.draw.gesture(canvas, result.gesture) // draw detected gesture results to canvas
 ```