Convolutional Neural Networks-Based Object Detection Algorithm by Jointing Semantic Segmentation for Images

Abstract

In recent years, increasing image data comes from various sensors, and object detection plays a vital role in image understanding. For object detection in complex scenes, more detailed information in the image should be obtained to improve the accuracy of detection task. In this paper, we propose an object detection algorithm by jointing semantic segmentation (SSOD) for images. First, we construct a feature extraction network that integrates the hourglass structure network with the attention mechanism layer to extract and fuse multi-scale features to generate high-level features with rich semantic information. Second, the semantic segmentation task is used as an auxiliary task to allow the algorithm to perform multi-task learning. Finally, multi-scale features are used to predict the location and category of the object. The experimental results show that our algorithm substantially enhances object detection performance and consistently outperforms other three comparison algorithms, and the detection speed can reach real-time, which can be used for real-time detection.

A Lightweight Semantic Segmentation Algorithm Based on Deep Convolutional Neural Networks

“…Their approach also applied the PointSIFT module, which can encode polydirectional information and adapt to the proportions of the shape being considered. Qiang et al [ 16 ] proposed an object detection algorithm by jointing semantic segmentation (SSOD) for images. They constructed a feature extraction network that mixed the hourglass structure network with an attention mechanism layer to extract multiscale features and allowed the algorithm for multitask learning.…”

Redefining Radiology - Artificial Intelligence Integration in Medical Imaging

“…AI algorithms efficiently interpret complex imaging data, identifying early stages of cardiac diseases like coronary artery disease and congestive heart failure using modalities such as cardiac CT, MRI, or echocardiography. For instance, ML models and CNNs have shown the ability to automatically detect calcification in coronary arteries and segment the left ventricular myocardium, respectively [67][68][69][70]. These automated processes have shown strong correlation with manual analyses.…”

A development of visual-feedback automatic control for robotic manipulator

“…The experiments show that our object size estimation method results in the highest accuracy at 98.87% and the tacking process can eectively keep the target object in the gripping position. Neural network [5][6][7][8] is used to provide the coordination with the target object also keep tracking accurate when the object moves. We employ Recurrent Neu-ral Network (RNN) due to its lower computational complexity compared to CNN [13][14].…”