The train wheelset is a crucial part of railway vehicles, and its damage may lead to serious safety accidents. Therefore, it is imperative to detect tread damage timely and accurately. With the rapid development of deep learning, the image detection method based on a convolutional neural network (CNN) has played an important role. Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the target detection field. The algorithm has achieved excellent results in target detection, but there is a low recognition rate for small targets. Therefore, we propose an improved SSD target detection algorithm. The Original SSD algorithm is ineffective in detecting small targets with pits and cracks, so conv3-3 is selected to join the detection. We optimize convolution kernel parameters; the convolution layer contains more small target details. Compared with the original SSD, the Mean Average Precision (MAP) of tread defect is improved by 4.38%, and the MAP of small target detection is enhanced by 7.24%. This algorithm has a better performance in detection accuracy.
Foreign fibers in cotton have serious adverse effects on the quality of textile products, so its effective identification and elimination has important significance and social value. To solve the above problems, we propose a fusion image pretreatment method based on limited contrast adaptive histogram equalization ( CLAHE ) and wavelet analysis ( WT ), The collected cotton polarization images were processed by WT & CLAHE, which effectively improved the contrast of anisotropic fibers in cotton images, and laid the foundation for the rapid and accurate identification of various anisotropic fibers in cotton in the later stage, It laid a foundation for the rapid and accurate identification of all kinds of anisotropic fibers in cotton in the later stage. Compared with manual and systematic detection, the results showed that technical personnel and detection system could accurately detect and identify dead leaves, white paper and color paper without interference from external environment and foreign fiber size. For white wool, hair and mulch film due to similar color or shape is small, technical personnel in the detection is easy to miss, and the detection system in WT & CLAHE image pretreatment, white wool, hair and mulch film detection accuracy is obviously due to artificial detection, especially for the mulch film this is not easy to detect foreign fiber has good recognition effect.
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.