Automatic detection of workers wearing safety helmets at the construction site is essential for safe production. Aiming at the problem of low recognition rate caused by factors such as background and light in the automatic detection of safety helmets using traditional machine learning methods, this paper proposes an object detection framework that combines Online Hard Example Mining (OHEM) and multi-part combination. In our framework, we first use the multi-scale training and the increasing anchors strategies to enhance the robustness of the original Faster RCNN algorithm to detect different scales and small object. Then, the OHEM is to optimize the model to prevent the imbalance of positive and negative samples. Finally, the person wearing the helmet and its parts (helmet and person) are detected by improved Faster RCNN. The multi-part combination method uses the geometric information of the detection objects to determine if a worker is wearing a helmet. Experiments show that compared with the original Faster RCNN, the detection accuracy is increased by 7%. It also has better detection performance for partial occlusion and different-size objects, showing good generalization and robustness.

In the detection of surface floating garbage, the existence of complex backgrounds and the small target sizes make the surface floating garbage easy to mis-detect. Existing approaches cannot yet provide a solution to the aforementioned problems and they are typically limited to addressing specific issues. This paper proposes a PC-Net algorithm for floating garbage detection. First, a pyramid anchor generation approach is proposed, which makes the anchor to be generated centrally near the target and reduces the interference of background information in the anchor generation. Then, in the RoI Pooling feature map import stage, the classification map is used as the feature map. This approach generates feature maps with a higher resolution and more distinct features, thereby enhancing the feature information of small targets and enhancing the classification accuracy. Experimental results on floating garbage dataset indicate that the average detection accuracy of the proposed approach is 86.4%. Compared with existing detection approaches, such as Faster R-CNN, YOLOv3, YOLOX, and Dynamic R-CNN, the average accuracy of detection is increased by 4.1%, 3.6%, and 2.8%, respectively.

The generation and propagation of internal waves in the ocean are a common phenomenon that plays a pivotal role in the transport of mass, momentum, and energy, as well as in global climate change. Internal waves serve as a critical component of oceanic processes, contributing to the redistribution of heat and nutrients in the ocean, which, in turn, has implications for global climate regulation. However, the automatic identification of internal waves in oceanic regions from remote sensing images has presented a significant challenge. In this research paper, we address this challenge by designing a data augmentation approach grounded in a modified deep convolutional generative adversarial network (DCGAN) to enrich MODIS remote sensing image data for the automated detection of internal waves in the ocean. Utilizing t-distributed stochastic neighbor embedding (t-SNE) technology, we demonstrate that the feature distribution of the images produced by the modified DCGAN closely resembles that of the original images. By using t-SNE dimensionality reduction technology to map high-dimensional remote sensing data into a two-dimensional space, we can better understand, visualize, and analyze the quality of data generated by the modified DCGAN. The images generated by the modified DCGAN not only expand the dataset’s size but also exhibit diverse characteristics, enhancing the model’s generalization performance. Furthermore, we have developed a deep neural network named “WaveNet,” which incorporates a channel-wise attention mechanism to effectively handle complex remote sensing images, resulting in high classification accuracy and robustness. It is important to note that this study has limitations, such as the reliance on specific remote sensing data sources and the need for further validation across various oceanic regions. These limitations are essential to consider in the broader context of oceanic research and remote sensing applications. We initially pre-train WaveNet using the EuroSAT remote sensing dataset and subsequently employ it to identify internal waves in MODIS remote sensing images. Experiments show the highest average recognition accuracy achieved is an impressive 98.625%. When compared to traditional data augmentation training sets, utilizing the training set generated by the modified DCGAN leads to a 5.437% enhancement in WaveNet’s recognition rate.

One-dimensional Otsu method is an adaptive threshold method which obtains the optimal threshold for image segmentation by the maximum between-class variance. Direct application of the Otsu segmentation method is very challenging due to the uniform background of the water surface image. In this paper, we propose an improved Otsu method based on uniformity measurement for segmentation of water surface. It achieves adaptive selection of thresholds by the uniformity measure function, so as to segment the surface floating object area better. Experimental results demonstrate that the effectiveness of the improved Otsu method is generally better than traditional Otsu method for the water surface images, which greatly improves the segmentation accuracy of images and reduces the mis-segmentation rate.

Software development social networking sites, such as Stack Overflow or CSDN, contain rich information on software functions. The SFF(Software Function Feature)-specific named entities could be mined from this information. And furthermore, the usage patterns of entities and issues-solutions could also be mined based on the recognition of SFF-specific named entities. However, the existing workes on named entity recognition mainly focuses on the medicine filed and news filed. In the field of software engineering, there is little research on software named entity recognition. In fact, the contents of Software Development Social Networking sites are always freeform texts, which is composed of source code, link, abbreviation and Chinese or English words. It brings some difficulties to the SFF-specific named entity recognition. So in this paper, we gives an approach for SFF-specific named entity recognition with the BI-LSTM(Bidirectional Long Short-Term Memory) model and word embedding technique. A preliminary empirical evaluation demonstrates that our approach is effective to recognize SFFspecific named entities in software development social networking sites contents.