Table 3 - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
displays that Yolo could better represent complex features of sock, but it is prone to overfitting and needs more data to train it. After epoch is 75000, it starts overfitting. TinyYolo is unable to represent complex features, although it is easier to train.
Source publication
We have used tinyYOLOV2 Neural Network to realize object detection and the aim is to detect specific three classes of objects (socks, slippers, wires) to prevent cleaning robots from being entangled by them. This work describes our methods of training neural network. Considering lack of related data sets, we have adopted various ways to process dat...
Similar publications
While the occlusion analysis of nanoparticles (NPs) has been important in detecting NPs in images, most existing methods fail to accurately segment contours, and additional time-consuming manual inspections are required. To overcome this issue, a new and effective quantum-mechanics-embedded NP occlusion analysis framework is proposed. The integrati...
In this paper, we propose a new few-shot learning method called StarNet, which is an end-to-end trainable non-parametric star-model few-shot classifier. While being meta-trained using only image-level class labels, StarNet learns not only to predict the class labels for each query image of a few-shot task, but also to localize (via a heatmap) what...
![Figure 1. Sensors used by the ADAS (Advanced Driver-Assistance System) [1].](profile/Dragan-Samardzija/publication/343515373/figure/fig1/AS:1073906437857280@1633050655650/Sensors-used-by-the-ADAS-Advanced-Driver-Assistance-System-1_Q320.jpg)
Most recent person re-identification approaches are based on the use of deep convolutional neural networks (CNNs). These networks, although effective in multiple tasks such as classification or object detection, tend to focus on the most discriminative part of an object rather than retrieving all its relevant features. This behavior penalizes the p...
Citations
This work proposes a lightweight object detection network model ShuffleNet-SSD (S-SSD) to solve the problem of single shot multibox detector (SSD) network model where it cannot meet the real-time performance requirement in the task of object detection and recognition of indoor mobile robot. This model is suitable for indoor mobile robot by improving the SSD network model based on ShuffleNet network. The main idea of the improvement is that S-SSD replaces VGG-16 network as the basic feature extraction network of SSD network model with ShuffleNet network. The proposed model is based on the design of deep separable convolution, point-by-point grouping convolution, and channel rearrangement. It retains the design idea of multiscale feature graph detection of SSD network model. This model ensures a slight decline in detection accuracy while greatly reduces the amount of computation generated by the network operation, thereby greatly improving the detection rate. A data set for the task of object detection and recognition of indoor mobile robot is made. The S-SSD lightweight network model is superior to the original SSD network model and tiny-YOLO lightweight network model in terms of detection accuracy and detection rate, and can simultaneously meet the requirement of detection accuracy and real-time performance in the task of indoor object detection and recognition of mobile robot. These findings are verified through the comparative experiments of object detection accuracy and detection rate and real-time object detection and recognition of mobile robot under the actual indoor scene.
