Apple detection during different growth stages in orchards using the improved YOLO-V3 model

TL;DR: In this paper, a two-stage pipeline consists of detecting the fruits, then tracking them frame-by-frame, using the You Only Look Once model (YOLO).

TL;DR: Wang et al. as discussed by the authors used the residual convolutional neural network ResNet 50 as backbone to extract features from the input image, adopts feature pyramid networks (FPN) for feature fusion, then generates a series of proposal boxes through region proposal network (RPN), and ultimately generates bounding boxes and corresponding classes by the classification network.

TL;DR: In this article , an intelligent transportation system (ITS)-based system that collects road event information via a vehicle's on-board unit (OBU) and roadside unit (RSU), integrates and processes information based on the database and the road network, and provides information to vehicles.

TL;DR: In this paper , a dual arm six-degree-of-freedom (6-DoF) collaborative robot, ABB YuMi, and a red, green, blue-depth (RGB-D) camera with YOLOv5 were used in a pick-and-place application.

TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.

TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.

TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.