基于改进ConvNeXt模型的黄羽鸡表皮层黑色素智能分级方法

为解决活体黄羽鸡表皮层黑色素分级方法成本高、效率低下、分级环境易受环境光干扰等问题,该研究探索一种基于ConvNeXt模型的黄羽鸡表皮层黑色素智能分级方法 ConvNeXt-WPCA,用于实现活体黄羽鸡表皮层黑色素智能分级。ConvNeXt-WPCA模型通过以下3点改进提高模型对黄羽鸡黑色素的识别效果：1）针对黄羽鸡黑色素图像RGB三通道内黑色素信息分布不均衡问题,改变输入图片通道权重来增强模型对黑色素特征的提取能力;2）使用部分卷积代替深度可分离卷积,减少模型计算量和内存访问次数提高对计算资源的利用率;3）引入坐标注意力机制,引导模型关注黄羽鸡胸腹部及肛门附近皮肤提升模型精度。同时,该研究还设计一种双光源图像获取装置,分别在自然光和偏振光条件下拍摄黄羽鸡样本,以减小分级结果受环境光干扰的影响,并探索偏振光在黑色素分级任务中的应用潜力。结果表明ConvNeXt-WPCA模型相较标准ConvNeXt模型,针对自然光下黄羽鸡黑色素图像数据集分级准确率提升9.68个百分点,最终达到89.03%的识别准确率,针对偏振光下黄羽鸡黑色素图像数据集分级准确率提升15.26个百分点,最终达到98.87...     

Effects of Cage Location and Tier Level with Respect to Light Intensity in Semiconfined Housing on Egg Production and Quality During the Late Laying Period

This experiment was conducted to determine the effects of cage location and tier level with respect to light intensity on egg production and egg quality of hens housed in a semiconfined facility. Hens (ISA Brown, n = 225) at 75 wk of age were placed into 3-tier cages as top (T), middle (M), and bottom (B) tiers located in cages illuminated artificially (EI), by window (FW), or between corridors (C) for 2 mo. Light intensity was measured monthly for each cage at 5 cm from feeders every 6 h. Egg production was recorded daily and egg quality was assessed biweekly. Light intensity was the greatest for cages in the FW group (151.9, 119.8, and 89.8 lx for tiers T, M, and B, respectively), followed by EI (52.6, 54.5, and 51.0 lx for tiers T, M, and B, respectively), and C (44.5, 23.4, and 4.7 lx for tiers T, M, and B, respectively). Hens at location EI had greater egg production than hens at FW and C. Egg production for hens at tier T was also greater than for hens at tiers M and B. Egg production for hens at EI and C decreased quadratically, whereas that for hens at FW decreased linearly from tiers T to B. Cage location, but not tier level, affected egg weight. Hens at EI and FW produced heavier eggs than hens at C. Shape index, yolk color, and yolk index were independent of cage location and tier level. Hens at EI and FW produced eggs with thinner and weaker shells than hens at C. Moreover, eggshell strength increased linearly from tier T to B. Both albumen index and Haugh unit were the greatest for hens at FW, followed by EI and C. Their responses to cage location varied with tier levels. In conclusion, variation in light intensity in multitier cage systems in semiconfined laying hen houses may be a contributing factor for depressed laying performance and egg quality.     

精口恶唑禾草灵抗性及敏感菵草种群萌发条件的比较

为了比较对精口恶唑禾草灵抗性及敏感菵草种群在萌发特性上的差异,采用培养皿法研究了温度、光照、pH值、水势、盐胁迫对其萌发的影响。结果表明,pH值为4-10条件下,2个种群的萌发率无显著性差异;全光照条件下,抗性菵草的萌发率显著低于敏感菵草;10℃条件下,抗性菵草的萌发率显著低于敏感菵草;水势胁迫和盐分胁迫对抗性菵草萌发的影响大于敏感菵草,当水势为-0.5 MPa时,抗性菵草无萌发,敏感菵草萌发率为41.9%;当NaC l溶液浓度为160 mmol/L时,抗性菵草无萌发,敏感菵草的萌发率为51.7%。     

光纤发光诱虫灯对茶树害虫的诱捕效果研究

为了对茶树害虫进行科学的测报和诱捕,设计了一种光纤发光诱虫灯,开展了光纤发光诱虫灯在不同发光颜色、不同亮灭规律的情况下与频振式杀虫灯对茶树害虫的诱集对比试验。试验结果表明:光纤发光诱虫灯在亮2min-灭1min的亮灭规律下诱虫效果和能耗均好于频振式杀虫灯;在绿、黄、蓝、白4种发光颜色中,黄色光诱虫效果最好。同时,进一步证实了频振式杀虫灯具有更好的杀虫稳定性;但对茶树害虫天敌也有很强的杀伤力,应科学制定开灯方案。综合诱虫效果、能耗和使用寿命,光纤诱虫灯具有良好的应用前景。     

基于激光雷达的巡检机器人导航系统研究

智能巡检机器人能够高效、可靠地完成巡检任务,降低工作人员的劳动强度,准确、稳定的导航定位是巡检机器人执行巡检任务的基础。本文研究了基于激光雷达的巡检机器人导航系统,可实现机器人在室内外环境下的地图建立、路径规划和导航定位。导航系统由远程监控平台与巡检机器人组成,远程监控平台发布巡检任务、监控机器人状态、查询与存储检测数据,巡检机器人可实现自主导航定位、遍历检测点、执行数据采集等巡检任务,二者通过无线网络实现远程数据交互。融合激光雷达与编码器信息,使用高鲁棒性Gmapping算法建立二维环境地图。根据地图与检测点信息,采用分支界定算法搜索最优巡检路线,以减少巡检时间和能源消耗。使用自适应蒙特卡罗定位(AMCL)算法估计机器人位置和姿态,结合巡检路线,进行导航定位。根据横向偏差与航向偏差,通过经典的PID算法完成机器人驱动控制。机器人搭载可见光相机与红外相机,可对目标进行可见光通道与红外通道的融合图像检测。对巡检机器人进行了室内导航定位试验,试验结果表明,在1 m/s的速度下,位置与航向偏差的平均绝对误差(MAE)分别小于5 cm和1.1°,标准差(SD)分别小于5 cm和1.5°,能够满足巡检导航定位的要求。     

道路草花景观对驾驶人员红灯敏感度的影响

近年来,随着对城市道路景观构建的重视,道路绿化、彩化景观愈发优美和引人注目。该文基于152份有效问卷,研究对比分析了3种道路灌-草层的绿化形式(绿篱式、50%草花覆盖式及100%草花覆盖式)对有驾驶经验的受访者红灯敏感度的影响。结果显示,相对于绿篱式道路绿化,草花式道路绿化会造成受访者红灯敏感度降低;女性比男性的红灯敏感度高,但更易受草花干扰;25—45岁年龄段受访者对红灯的敏感度和抗草花干扰能力比18—25岁及45岁以上受访者高;相对于偏好草花式绿化的受访者,偏好绿篱式绿化的受访者有更高的红灯敏感度和抗草花干扰能力。建议应尽量避免在事故易发地段大面积应用颜色艳丽的草花进行道路绿化。     

烤烟优质高产栽培的生理基础研究 Ⅰ.烟草品种光温反应的发育特性研究

采用定日长与分期播种相结合的方法,研究了我国烟草现用主体品种的光、温反应的发育特性。结果表明:(1)较低温度可促进烟草花芽分化;(2)大多数品种对日长的反应不敏感,属日中性。另外,还研究了花芽分化的叶龄指标。     

四个观赏海棠品种光合特性比较研究

为比较引种观赏海棠品种间光合特性,以海棠粉芽、红宝石、凯尔斯和绚丽为试材,测定了净光合速率(Pn)、胞间CO2浓度(Ci)、气孔导度(Gs)、蒸腾速率(Tr)等光合生理指标和光响应曲线.结果表明:凯尔斯净光合速率的日变化呈单峰型,但粉芽、红宝石和绚丽的净光合速率的日变化呈双峰型.胞间CO2浓度日变化均呈V型曲线变化,均...     

Estimation of litchi (Litchi chinensis Sonn.) leaf nitrogen content at different growth stages using canopy reflectance spectra

The estimation of crop nitrogen status in fresh vegetation leaf using field spectroscopy is challenging due to the weak responses on leaf/canopy reflectance and the overlapping with the absorption features of other compounds. Although the spectral indices were proposed in the literature to predict leaf nitrogen content (LNC), the performance of selected spectral indices to estimate the LNC is often inconsistent. Moreover, the models for nitrogen content estimation changed with the growth stage. The goal of this study was to evaluate the performance of published indices, ratio of data difference index (RDDI) and ratio of data index (RDI) developed by band iterative-optimization algorithm in LNC estimation. The correlation analysis, linear regression and cross validation were used to analyze the relationship between spectral data and LNC and construct the best performed estimation model. The study was conducted by the data of five growing seasons of litchi from the orchards in Guangdong Province of China. Results showed that the relationship between chlorophyll (Chl) related spectral indices and LNC varied with the growth stage. Even in flower bud morphological differentiation stage and autumn shoot maturation stage, there were not significant correlations between the proposed spectral indices and LNC. Besides it is difficult to estimate the LNC by the general model across the growth stages due to the integrated effects of cultivar, biochemical, canopy structure, etc. The band iterative-optimization algorithm can improve the sensitivity of spectral data to LNC to some extent. The optimal RDDI performed better than other indices for the synthetic dataset and the dataset in each growth stage. And the sensitive bands selected in the optimal indices at each growth stage are not consistent, which are not only related to the Chl absorption but also other biochemical components, such as starch, lignin, cellulose, protein, etc. In general, the LNC can be estimated by the optimized CR-based RDDI indices in autumn shoot maturation stage, flower spike stage, fruit maturation stage, and flowering stage with the R² > 0.50 and RMSE < 0.14. Although there were the significant relationship between RDIs and RDDIs in flower bud morphological differentiation stage, the highest R²s of the model developed by RDDIs and RDIs were less than 0.50 in cross validation. This study indicated that the applicability of canopy reflectance to estimate litchi LNC was closely related to the growth stage of litchi. Growth stage-specific models will be preferred for estimating litchi LNC estimation.     

Use of Canopy Temperature Measurements as a Screening Tool for Drought Tolerance in Spring Wheat

Remotely sensed infrared canopy temperatures provide an efficient method for rapid, non-destructive monitoring of whole-plant response to water stress. Field studies were conducted in 1992 and 1993 to evaluate the potential for using canopy temperatures to screen for drought tolerance in wheat. In both years, 12 spring wheat (Triticum aestivum L.) genotypes were grown under two irrigation levels (well-watered and moisture-stressed) imposed between tillering and anthesis with a line-source sprinkler irrigation system. Canopy temperature measurements were taken in well-watered and moisture-stressed plots between 1330 and 1430 h (MDT) on five clear days in 1992 and seven clear days in 1993 during the late vegetative and early reproductive growth periods following closure of the plant canopy. Genotypes exhibited differences in mean canopy temperatures across the two irrigation levels and two years. Klasic consistently had the highest canopy temperature under moisture-stressed conditions, while Bannock and Pondera had the lowest. Bannock, Yecora Rojo and Klasic had the warmest canopies under well-watered conditions, while Vandal, Amidon and Rick had the coolest. Plot-to-plot variation in canopy temperature under water stress conditions was evident for differences in grain yield. Significant correlations between canopy temperature and yield under moisture-stress conditions and drought susceptibility index values indicated the potential for screening wheat genotypes for drought response.