In dynamic SLAM (Simultaneous Localization and Mapping), machine vision needs to understand and closely align with human cognitive semantics to overcome the interference from moving objects. DeepLabV3+ is a mainstream semantic segmentation algorithm that balances accuracy and speed. However, DeepLabV3+ does not differentiate the weights of various feature layers, does not address the issue of sample imbalance, and has a large parameter count in its backbone network. To tackle these issues, this paper proposes a method that introduces an attention mechanism during the fusion of the algorithm's multi-scale feature information, emphasizing important information and enhancing the ability to recover boundaries. A new lightweight extraction network is used as the backbone, and a more appropriate loss function is employed to balance the segmentation targets, thereby improving the final segmentation results. Experimental results show that while the mean Intersection Over Union (mIOU) on the PASCAL VOC 2007 dataset decreases by about 5 percentage points, the model's parameters are significantly reduced by about 89%. This reduction in parameters maintains the accuracy of feature extraction and significantly improves object segmentation performance in dynamic scenes on mobile devices.
Due to the immaturity of printing technology, printing defect is an inevitable problem in industrial production. It will greatly affect the appearance and performance of the product if defects could not be found and dealt with in time. Defect detection often requires high real-time performance and registration rate. Especially in the case of angular shift or image translation, the algorithm needs to have good registration effect. Feature matching is an important part of image registration. In the actual detection process, the speed and quality of matching directly affect the results of image registration algorithm. Based on deep understanding of SIFT, SURF, ORB and GMS, in the case of different lighting environments, different shooting angles, scale changes and fuzzy images, the superposition effect, registration time, number of feature point pairs and registration rate of four typical feature matching algorithms above are compared on the open data set respectively. The robustness, speed, advantages and disadvantages as well as applicable conditions of those four algorithms are analyzed and summarized. And an appropriate algorithm is selected based on the actual defect detection task. Experimental results show that ORB algorithm has the characteristics of fast speed, high registration rate and strong robustness in different environments. So, it is adopted in the actual defect detection task. Actual defect detection results show that ORB algorithm can not only accurately frame the defect area of printed matter, but also well meet the real-time production requirements of defect detection.
With the rise of the new generation of artificial intelligence technology, the object detection method based on deep learning has achieved remarkable results. In this paper, the detection accuracy of three popular object detection algorithms such as You Only Look Once (YOLO V3), Region-CNN (Faster R-CNN) and Single Shot MultiBox Detector (SSD) has been compared. Aiming at the actual detection problems of building block parts with irregular shape and different sizes, a method that combines deep convolutional generative adversarial networks (DCGAN) with deep learning based object detection algorithm is proposed to solve the problems of over fitting or weak generalization ability in the case of limited datasets, and to improve the detection accuracy of object detection algorithm. Experimental results show that: 1. Using public datasets, when the training data is reduced, the mean average precision (mAP) values of the above three algorithms are reduced respectively. Among those, SSD algorithm has the smallest change, which decreases 7.81%. 2. The control variable method is used to train the building block parts. In the case of insufficient training data, the detection accuracy of three object detection algorithms is low. 3. After combining SSD algorithm with DCGAN algorithm and applying it into the detection task of building block parts, the mAP value is improved from 79.63% to 83.32%, and the detection accuracy is obviously improved.
When a feature point detection method is used in vision SLAM to match images, environment condition around the robot is uncertain usually. Many influence factors such as rotation, scale, fuzzy as well as illumination in the process of detection have a strong impact on robot's locating and incremental map building. Experiments proved that SIFT, SURF, BRISK, ORB and FREAK have good robustness under normal illumination. However, the illumination is complex in practical applications, and the stability of image features extraction will be affected. Based on a mobile robot vision platform, the speed, repetition rate and matching rate of five feature extraction algorithms above are compared and analyzed with different methods. Under dynamic illumination, the robustness and matching effect of image features with translation, rotation, scale and fuzzy transformations are also compared. Through experimental data analyzing, BRISK features shows better effect under dynamic illumination.
control method based on visual servo feedback is proposed, which is used to improve the attitude of a quad-rotor
aircraft and to enhance its flight stability. Ground target images are obtained by a visual platform fixed on aircraft. Scale
invariant feature transform (SIFT) algorism is used to extract image feature information. According to the image
characteristic analysis, fast motion estimation is completed and used as an input signal of PID flight control system to
realize real-time status adjustment in flight process. Imaging tests and simulation results show that the method proposed
acts good performance in terms of flight stability compensation and attitude adjustment. The response speed and control
precision meets the requirements of actual use, which is able to reduce or even eliminate the influence of environmental
disturbance. So the method proposed has certain research value to solve the problem of aircraft’s anti-disturbance.
KEYWORDS: Data acquisition, Data communications, Transceivers, Sensors, Telecommunications, Wireless communications, Micro unmanned aerial vehicles, Environmental monitoring, Humidity, Control systems
For overcoming the problems such as remote operation and dangerous tasks, multi-terminal remote monitoring and warning system based on STC89C52 Micro Control Unit and wireless communication technique was proposed. The system with MCU as its core adopted multiple sets of sensor device to monitor environment parameters of different locations, such as temperature, humidity, smoke other harmful gas concentration. Data information collected was transmitted remotely by wireless transceiver module, and then multi-channel data parameter was processed and displayed through serial communication protocol between the module and PC. The results of system could be checked in the form of web pages within a local network which plays a wireless monitoring and warning role. In a remote operation, four-rotor micro air vehicle which fixed airborne data acquisition device was utilized as a middleware between collecting terminal and PC to increase monitoring scope. Whole test system has characteristics of simple construction, convenience, real time ability and high reliability, which could meet the requirements of actual use.
Research on LWIR multispectral imaging detection technology carried out in the key national defense laboratory in
Tianjin University is introduced in this paper. Firstly, a kind of infrared multispectral image simulation method based on
multispectral or hyperspectral images data in the VIS/NIR band is recommended. The combined strategy of
unsupervised and supervised classification methods is put forward to efficiently realize auto-matching and labeling of
pixels. Then, using the infrared image simulation technology, infrared multispectral simulation images can be generated
highly similar to real natural environments, which are valuable to the development of LWIR multispectral spectrometers,
as well as research on multispectral detection algorithms. Secondly, the co-image plane imaging detection technique is
presented as well as the attempt to make the small LWIR multispectral imaging detector based on such concept. A fourband
prototype has been achieved in VIS/NIR band, verifying the feasibility and validity of this technique.
Applications of stroboscopic imaging technique in different areas are illuminated. Several major three-dimensional
morphology imaging detection methods for micro flexible adaptive aerodynamic shape, which are based on scaled model
in experiment process, are discussed at home and abroad at present. And stroboscopic imaging detection technique and
testing device are introduced emphatically, which could be used to obtain deformation information of flexible aerodynamic shape. A flexible aerodynamic shape detection method, based on the combination of stroboscopic imaging
technique and optical flow analysis, is proposed to validate experimental model for adaptive aerodynamic shape. This
technique could compensate the inadequacy of numerical analysis and provide more aeroelastic characteristics for
further analysis. Moreover, this measurement method is of advantages such as non contact, real time and visualization etc.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.