Nondestructive perception of potato quality in actual online production based on cross-modal technology

Nowadays,China stands as the global leader in terms of potato planting area and total potato production.The rapid and nondestructive detection of the potato quality before processing is of great significance in promoting rural revitalization and augmenting farmers’income.However,existing potato quality sorting methods are primarily confined to theoretical research,and the market lacks an integrated intelligent detection system.Therefore,there is an urgent need for a post-harvest potato detection method adapted to the actual production needs.The study proposes a potato quality sorting method based on cross-modal technology.First,an industrial camera obtains image information for external quality detection.A model using the YOLOv5s algorithm to detect external green-skinned,germinated,rot and mechanical damage defects.VIS/NIR spectroscopy is used to obtain spectral information for internal quality detection.A convolutional neural network(CNN)algorithm is used to detect internal blackheart disease defects.The mean average precision(mAP)of the external detection model is 0.892 when intersection of union(IoU)=0.5.The accuracy of the internal detection model is 98.2%.The real-time dynamic defect detection rate for the final online detection system is 91.3%,and the average detection time is 350 ms per potato.In contrast to samples collected in an ideal laboratory setting for analysis,the dynamic detection results of this study are more applicable based on a real-time online working environment.It also provides a valuable reference for the subsequent online quality testing of similar agricultural products.

Effect of Irrigation Method and Non-Uniformity of Irrigation on Potato Performance and Quality

Potato growth, yield, and quality under improved irrigation methods and non-uniformity of their irrigation applications are important to enhance water management in arid regions. A field experiment was conducted in 2014 spring and fall growing seasons using potato (Solanum tuberosum) grown in northern Egypt at Shibin El Kom, Menofia, Egypt to evaluate potato response to furrow or trickle irrigation. A Randomized Split-Plot Design with irrigation method randomly distributed and non-uniformity of irrigation applications evaluated along either irrigation furrow or trickle lateral as dependent variables measured at the 3rd, 13th, 23rd, 33rd, 43rd and 53rd m along the 55 m irrigation line. Traditional (TF) and partial (PF) furrows as well as trickle point (TP) and line (TL) sources were used as irrigation methods. Each treatment was repeated three times. For a 33rd m treatment, seasonal optimum water use by potato was 328, 234, 269 and 292 mm over 118 days in spring and 200, 164, 178 and 186 mm over 122 days in fall under TF, PF, TP and TL irrigation methods, respectively. Potato tuber yield and quality were significantly affected by growing season (S), irrigation method (I) and non-uniformity of irrigation application (U). Tuber yield, total soluble solid (TSS) and leaf area index (LAI) were significantly affected by I and U, and their interaction I * U;harvest index (HI) was not affected by I but U. Except for TSS by S * I and HI by U * I and S * I, results showed no significant differences. Moreover, tuber weight, number and marketable yield were significantly affected by S, I, U and I * U interaction, except medium tuber size and culls by S. A given 33rd treatment under partial furrow and trickle irrigation, relative to that of traditional furrow, enhanced tuber yield and improved quality in both growing seasons. In non-un- iform irrigation application over two growing seasons, potato crop response was developed under varied irrigation methods. Tuber yields were significantly affected in a linear relationship (r2 ≥ 0.75) by either water deficit or excessive water under irrigation methods.