Corn is a globally important economic crop. Certain trait parameters of corn ears kernels per ear are essential indicators for corn breeding. However, acquiring these parameters faces two challenges: i) manual measurement is labor-intensive and error-prone, and ii) vision-based corn phenotyping machines require fixed image capturing environment and are cost-prohibitive. To address these limitations, we introduce CornPheno, a user-friendly, low-end, smartphone-based approach capable of executing corn ear phenotyping in the wild. CornPheno highlights three corn ear parameters: kernels per ear, rows per ear, and kernels per row. Technically, inspired by crowd localization in computer vision, we first extract kernels per ear based on a Corn data-trained Point quEry Transformer (CornPET). CornPET generates interpretable per-kernel point predictions and supports subsequent row detection. To detect rows, we introduce a novel point-based corn row detection approach, termed unicorn, featured by sqUeezed clusteriNg and bI-direCtional pOint seaRchiNg, to phenotype rows per ear and kernels per row. With adaptive geometric modeling, our approach is robust to partial rows, curved rows, and missing kernels. To promote the use of CornPheno, we have integrated it into OpenPheno, a WeChat-based mini-program, and made it open-access for corn breeders. We hope our approach can provide the community with a user-friendly and cost-effective way to facilitate corn breeding.
WIFI base stations have full indoor coverage, and the inertial navigation system (INS) is independent and autonomous, with high short-term positioning accuracy. However, errors accumulate over time, and an INS/WIFI combination has become the mainstream research direction regarding indoor positioning technology. The accuracy of WIFI fingerprint maps deteriorates significantly with changes in the environment or time, and there is an urgent need to solve the problem of automatic real-time updating of fingerprint maps. This article addresses the issue that the existing real-time acquisition technology for fingerprint point locations has severely restricted the real-time updating of fingerprint maps. For the first time, landmark points are introduced into the fingerprint map, and landmark point fingerprints are defined to construct a new fingerprint map database structure. A method for automatic recognition of landmark points (turning points) based on inertial technology is proposed, which achieves automatic and accurate collection of landmark point fingerprints and improves the reliability of crowdsourcing data. Real-time automatic monitoring of fingerprint signal fluctuations at landmark points and construction of error models have achieved real-time and accurate updates of fingerprint maps. Real scene experiments have shown that the proposed solution significantly improves the long-term stability and reliability of fingerprint maps.