Automated lane marking detection is essential for advanced driver assistance system (ADAS) and pavement management work. However, prior research has mostly detected lane marking segments from a front-view image, which easily suffers from occlusion or noise disturbance. In this paper, we aim at accurate and robust lane marking detection from a top-view perspective, and propose a deep learning-based detector with adaptive anchor scheme, referred to as A2-LMDet. On the one hand, it is an end-to-end framework that fuses feature extraction and object detection into a single deep convolutional neural network. On the other hand, the adaptive anchor scheme is designed by formulating a bilinear interpolation algorithm, and is used to guide specific-anchor box generation and informative feature extraction. To validate the proposed method, a newly built lane marking dataset contained 24,000 high-resolution laser imaging data is further developed for case study. Quantitative and qualitative results demonstrate that A2-LMDet achieves highly accurate performance with 0.9927 precision, 0.9612 recall, and a 0.9767 [Formula: see text] score, which outperforms other advanced methods by a considerable margin. Moreover, ablation analysis illustrates the effectiveness of the adaptive anchor scheme for enhancing feature representation and performance improvement. We expect our work will help the development of related research.
Two gelatin‐hydrolyzing proteinases with molecular masses of 85 and 72 kDa in the sarcoplasmic fraction of grass carp muscle were detected using gelatin zymography. The gelatinolytic activity in dark muscle was obviously higher than that in white muscle. Optimum pH and temperature of the two enzymes were around 8.0 and 40C. The proteinase inhibitor leupeptin entirely inhibited GP‐I, but E‐64 did not inhibit it. Only EDTA completely suppressed GP‐II, and Ca2+ is essential for the activity of GP‐II. All these facts indicated that GP‐I was matrix serine proteinase, and GP‐II was matrix metalloproteinase. When grass carp muscle was stored for 15 days at 4C, GP‐I and GP‐II were detected during the whole stored period. Therefore, the two gelatinolytic proteinases may be proposed to participate in the tenderization of fish muscle during postmortem stage.
PRACTICAL APPLICATIONS
Gelatinolytic proteinases from grass carp can effectively hydrolyze gelatin. These proteinases may be used to hydrolyze gelatin for peptide that has been added to food products as additive to improve texture. In addition, this study will be significant to learn and comparatively study the properties of gelatinolytic proteinases in fresh fish. Furthermore, this study will surely be beneficial for understanding the mechanism of postmortem tenderization of fish muscle.
Abstract. With the deepening research and cross-fusion in the modern remote sensing image area, the classification of high spatial resolution remote sensing images has captured the attention of the researchers in the field of remote sensing. However, due to the serious phenomenon of “same object, different spectrum” and “same spectrum, different object” of high-resolution remote sensing image, the traditional classification strategy is hard to handle this challenge. In this paper, a remote sensing image scene classification model based on SENet and Inception-V3 is proposed by utilizing the deep learning method and transfer learning strategy. The model first adds a dropout layer before the full connection layer of the original Inception-V3 model to avoid over-fitting. Then we embed the SENet module into the Inception-V3 model for optimizing the network performance. In this paper, global average pooling is used as squeeze operation, and then two fully connected layers are used to construct a bottleneck structure. The model proposed in this paper is more non-linear, can better fit the complex correlation between channels, and greatly reduces the amount of parameters and computation. In the training process, this paper adopts the transfer learning strategy, makes full use of existing models and knowledge, improves training efficiency, and finally obtains scene classification results. The experimental results based on AID high-score remote sensing scene images show that SE-Inception has faster convergence speed and more stable training effect than the original Inception-V3 training. Compared with other traditional methods and deep learning networks, the improved model proposed in this paper has greater accuracy improvement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.