From 4c680b2b09cbc5cc228a58a2c3689df568619f5d Mon Sep 17 00:00:00 2001
From: Michael Pivato <pivmy004@mymail.unisa.edu.au>
Date: Mon, 14 Jan 2019 12:25:26 +1030
Subject: [PATCH] Add code to for hand detection using CNN

---
 GestureRecognition/SimpleHandRecogniser.py | 79 +++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)

diff --git a/GestureRecognition/SimpleHandRecogniser.py b/GestureRecognition/SimpleHandRecogniser.py
index d81171a..3548a87 100644
--- a/GestureRecognition/SimpleHandRecogniser.py
+++ b/GestureRecognition/SimpleHandRecogniser.py
@@ -119,4 +119,81 @@ class SimpleHandRecogniser(HandRecogniser):
             prev_x = x
             prev_y = y
 
-        return num_change / 2 - 1
\ No newline at end of file
+        return num_change / 2 - 1
+
+    def detect_hand(self, weights_path, config_path, conf_thresh = 0.5, nms_thresh = 0.4):
+        '''
+            Detects if there is a hand in the image. If there is (above a significant confidence threshold)
+            then the function will set the img property to the location of the hand according to its bounding box. 
+        '''
+        # Most of this code is from here: www.arunponnusamy.com/yolo-object-detection-opencv-python.html
+        # Also https://github.com/opencv/opencv/blob/3.4/samples/dnn/object_detection.py
+        if self.img is None:
+            return 0
+
+        height = self.img.shape[0]
+        width = self.img.shape[1]
+        scale = 0.5
+
+        classes = None # Stores classes used for classification
+
+        net = cv2.dnn.readNet(weights_path, config_path)
+
+        net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
+
+        outNames = net.getUnconnectedOutLayersNames()
+
+        blob = cv2.dnn.blobFromImage(self.img, scale, (416,416), (0,0,0), True, False)
+
+        net.setInput(blob)
+
+        outs = net.forward(outNames)
+
+        # Getting the output layer.
+        layerNames = net.getLayerNames()
+        lastLayerId = net.getLayerId(layerNames[-1])
+        lastLayer = net.getLayer(lastLayerId)
+
+        classIds = []
+        confidences = []
+        boxes = []
+        if lastLayer.type == 'DetectionOutput':
+            # Check we are using an actual detection module. 
+            # Will return a 1x1xnx7 blob, where n is number of detections.
+            # Tuple for each detection: [batchId, classId, confidence, left, top, right, bottom]
+
+            for out in outs:
+                for detection in out[0,0]:
+                    confidence = detection[2]
+                    if confidence > conf_thresh:
+                        # WIll need to verify this first, but given code said this is needed. 
+                        left = int(detection[3] * width)
+                        top = int(detection[4] * height)
+                        right = int(detection[5] * width)
+                        bottom = int(detection[6] * height)
+                        classIds.append(int(detection[1]) - 1)
+                        confidences.append(float(confidence))
+                        boxes.append((left, top, right, bottom))
+
+
+        # Remove duplicate/overlapping boxes -> makes sure only detect one hand in an area.
+        indices = cv2.dnn.NMSBoxes(boxes, confidences, conf_thresh, nms_thresh)
+
+        for i in indices:
+            i = i[0]
+            box = boxes[i]
+            left = box[0]
+            top = box[1]
+            right = box[2]
+            bottom = box[3]
+            # Now draw the box if we want to.
+
+        # OR can just get the box that is a hand with the maximum confidence/maximum box area -> this implies closest hand...
+        max_conf = 0
+        max_index = 0
+        for conf in confidences:
+            if conf > max_conf:
+                max_conf = conf
+                max_index = i
+
+