Fresh Tea Sprouts Detection via Image Enhancement and Fusion SSD

Figure 2

Network architecture of the proposed FTSD-IEFSSD method; the ResNet50 is used as the backbone of each subnetwork (conv1–5), and the extra convolutional layers and prediction layer follow the same design as the conventional SSD. An RGB-channel-transform-based image enhancement algorithm is proposed to get the enhanced image, which can provide more input information. The fusion features (enhanced conv3) are obtained from the semantic fusion of conv3–6, and the bilinear interpolation is employed in conv4–6 to align the same size of conv3. The score fusion is also employed to achieve the fresh tea sprouts detection.