Depth extraction in computational integral imaging based on bilinear interpolation

Huang, Huihua; Ge, Peng

doi:10.37190/oa200401

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regard to the cross-stage integration mechanism, the con operation with a kernel size of 3*3 was exploited to improve the local perception tence of the model and the quantity of 1*1 convolution kernel could flexibly ad stacking of channels. Moreover, the double upsampling processes after feature int were implemented through bilinear interpolation [53]. The SE block, depicted in Figure 4, serves as a lightweight plug-and-play channel attention mechanism.…”

Section: Image Feature Learning Networkmentioning

confidence: 99%

A Tiny Object Detection Approach for Maize Cleaning Operations

Yu,

Li,

et al. 2023

Foods

View full text Add to dashboard Cite

Real-time and accurate awareness of the grain situation proves beneficial for making targeted and dynamic adjustments to cleaning parameters and strategies, leading to efficient and effective removal of impurities with minimal losses. In this study, harvested maize was employed as the raw material, and a specialized object detection network focused on impurity-containing maize images was developed to determine the types and distribution of impurities during the cleaning operations. On the basis of the classic contribution Faster Region Convolutional Neural Network, EfficientNetB7 was introduced as the backbone of the feature learning network and a cross-stage feature integration mechanism was embedded to obtain the global features that contained multi-scale mappings. The spatial information and semantic descriptions of feature matrices from different hierarchies could be fused through continuous convolution and upsampling operations. At the same time, taking into account the geometric properties of the objects to be detected and combining the images’ resolution, the adaptive region proposal network (ARPN) was designed and utilized to generate candidate boxes with appropriate sizes for the detectors, which was beneficial to the capture and localization of tiny objects. The effectiveness of the proposed tiny object detection model and each improved component were validated through ablation experiments on the constructed RGB impurity-containing image datasets.

show abstract

Section: Image Feature Learning Networkmentioning

confidence: 99%