Unsupervised Classification Algorithm for Early Weed Detection in Row-Crops by Combining Spatial and Spectral Information

Abstract

Abstract:In agriculture, reducing herbicide use is a challenge to reduce health and environmental risks while maintaining production yield and quality. Site-specific weed management is a promising way to reach this objective but requires efficient weed detection methods. In this paper, an automatic image processing has been developed to discriminate between crop and weed pixels combining spatial and spectral information extracted from four-band multispectral images. Image data was captured at 3 m above ground, with a camera (multiSPEC 4C, AIRINOV, Paris) mounted on a pole kept manually. For each image, the field of view was approximately 4 m × 3 m and the resolution was 6 mm/pix. The row crop arrangement was first used to discriminate between some crop and weed pixels depending on their location inside or outside of crop rows. Then, these pixels were used to automatically build the training dataset concerning the multispectral features of crop and weed pixel classes. For each image, a specific training dataset was used by a supervised classifier (Support Vector Machine) to classify pixels that cannot be correctly discriminated using only the initial spatial approach. Finally, inter-row pixels were classified as weed and in-row pixels were classified as crop or weed depending on their spectral characteristics. The method was assessed on 14 images captured on maize and sugar beet fields. The contribution of the spatial, spectral and combined information was studied with respect to the classification quality. Our results show the better ability of the spatial and spectral combination algorithm to detect weeds between and within crop rows. They demonstrate the improvement of the weed detection rate and the improvement of its robustness. On all images, the mean value of the weed detection rate was 89% for spatial and spectral combination method, 79% for spatial method, and 75% for spectral method. Moreover, our work shows that the plant in-line sowing can be used to design an automatic image processing and classification algorithm to detect weed without requiring any manual data selection and labelling. Since the method required crop row identification, the method is suitable for wide-row crops and high spatial resolution images (at least 6 mm/pix).

Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images

“…However, this technique requires precise modeling in terms of texture, 3D models, and light conditions. In [34], an automatic image processing method was developed to discriminate between crop and weed pixels by combining spatial and spectral information extracted from four-band multispectral images. Image data were captured at 3 m above ground with a camera mounted on a manually held pole.…”

“…This method was applied to only one field, but we have found that the feature selection approach, even with random forest, is not robust when the field or crop type changes. In [34], an automatic image processing method was developed to discriminate between crop and weed pixels on images acquired by a camera mounted on a manually held pole. The authors combined spatial and spectral information extracted from four-band multispectral images.…”

A Weakly Supervised Deep Learning Framework for Sorghum Head Detection and Counting

“…Machine learning and image processing have proved their utility in diverse fields. Especially in the field of plant phenotyping [2][3][4][5][6][7], these tools have laid a strong foundation in detecting multiple crop diseases [8] as well as making sense of disease severity without the need for any additional human supervision [8], crop/weed discrimination [9][10][11][12], canopy/individual extraction [13,14], fruit counting/flowering [15][16][17], and head/ear/panicle counting [18][19][20]. Our hypothesis is that machine learning and image processing along with unmanned aerial vehicles (UAV) based photogrammetry is a reliable alternative to the laborintensive sorghum head survey in the field [21][22][23].…”

Sentinel-2 Validation for Spatial Variability Assessment in Overhead Trellis System Viticulture Versus UAV and Agronomic Data

“…All these papers describe applications on vertical pruning systems (VPS), the most widespread class of training systems used in quality viticulture, which presents a discontinuous spatial layout with vegetated rows alternating with soil [54,55]. In these cases, spatial analysis of remote sensing images requires separation of the canopy from bare soil, shadows, and green cover, which can be achieved with advanced filtering techniques for canopy extraction [56][57][58][59][60]. Many authors suggest unsupervised filtering techniques in a vineyard based on a canopy height model (CHM) derived from a digital elevation model (DEM) [51,53], geometric structure by texture analysis [61,62], 3D point cloud [63], automatic threshold on color distribution in RGB [64], different color spaces such as HSV (hue, saturation, value), or L*a*b* (L* for the lightness from black to white, a* from green to red and b* from blue to yellow) [65].…”