This paper focuses on the development of maize plant datasets for the purposes of recognizing maize plants and weed species, as well as the precise automated application of herbicides to the weeds. The dataset includes 36,374 images captured with a high-resolution digital camera during the weed survey and 500 images annotated with the Labelmg suite. Images of the eighteen farmland locations in North Central Nigeria, containing the maize plants and their associated weeds were captured using a high-resolution camera in each location. This dataset will serve as a benchmark for computer vision and machine learning tasks in the intelligent maize and weed recognition research.

Agriculture and agribusinesses suffer from many challenges, despite their significance to global economic growth. One of the challenges is the lack of appropriate technology to drive the industry to the next level of development. This technological gap contributes to reduced yield and profit without a reduction in manual labour, cost, and stress. Robotics have been explored to boost agricultural production and improve agribusiness productivity. Several weed control robots have been developed for research and field uses, but these systems are not suitable for weed control in large commercial farms or lack control schemes for navigation and weed control. This study presents the design of an autonomous robot system for chemical weed control. The system uses control theory, artificial intelligence, and image processing to navigate a farm environment, identify weeds, and apply herbicide where necessary. Upon implementation and adoption, this system would increase agricultural productivity with minimal human input, thereby leading to an increase in revenue and profit for agribusinesses.

A two–year experiment was carried out to determine the effects of tillage (heap and level, hoe plough and herbicide-based zero tillage) and weed control methods (no weeding, hoe weeding at 25 days after transplanting (DAT), hoe weeding at 25 and 45 DAT, application of post-emergence herbicide propanil plus 2,4-D (Orizo Plus, Proficol Calle, Baranquilla, Colombia) at 25 DAT followed by hoe weeding at 45 DAT, and Orizo Plus® at 25 and 45 DAT) on weed infestation and performance of lowland rice in Badeggi, Nigeria. Reduced weed density and biomass, taller rice plants, and higher panicle and paddy yield were recorded in most heap and level treatments. Two hoe weedings only and Orizo Plus® at 25 DAT followed by one hoe weeding resulted in significantly lower weed density and biomass, more panicles and significantly higher paddy yield. Hoe plough in combination with two hoe weedings had the lowest weed density. Zero tillage planting in combination with two hoe weedings produced weed biomass comparable to heap and level in combination with the application of Orizo Plus® at 25 DAT followed by one hoe weeding. These results suggest that hoe plough followed by hoe weeding at 25 and 45 DAT, or heap and level tillage followed by application of Orizo Plus® at 25 DAT and hoe weeding at 45 DAT effectively controlled weeds and increased plant height, panicle number and paddy yield of transplanted rice.

Integration of herbaceous legume Aeschynomene histrixinto the farmers’ cropping system is one viable option that can improve the nutrition of maize (Zea mays), increase soil physical, chemical and biological properties which can result in sustainable Striga control and crop productivity. This study was conducted to determine the effects of A. histrix fallow and N fertilizer application on Strigainfestation, growth and yield of maize. The study involved the factorial combination of fallow type: natural fallow (NF) and A. histrix fallow (AF), and inorganic N fertilizer application: 0, 30, 60 and 90 kg N ha^-1 arranged in a split plot in a randomised complete block design and replicated three times. Results show that cropping/maize after A. histrix fallow significantly (P < 0.05) delayed Strigaemergence, reduced its virulence on the host crop, increased maize plant height, and grain yield compared to natural fallow. Application of 90 kg N ha^-1 delayed days to Striga shoot emergence, reduced Striga damage on host crop, and increased plant height of maize. Heavier and higher grain yield of maize were significantly associated with of 60 kg N ha^-1. Integrating A. histrix fallow rotations with application of 60 kg N ha^-1 can provide sustainable Strigacontrol, and A. histrix in combination with 90 kg N ha^-1 modest yield of maize. This study has shown that farmers in the southern Guinea savanna location of Nigeria can effectively control Striga and obtain better maize yield by integrating A. histrix fallow with the application of N fertilizer. Keywords:  Striga, Aeschynomene histrix, fallow rotation, nitrogen, maize