Posted on

narvidia weed seeds

So they rigged together a crude demo to show that a GeForce GPU could run a weed-identification network with a camera. And next thing you know, they had their first customer-investor.

“You need to apply the right amount of herbicides to weeds — if you apply too little, the weed will keep growing and creating new seeds. Bilberry can do this at a rate of 242 acres per hour, with our biggest unit” said Serrat.

Farm Tech 2.0

Today, the sustainability race is on to treat “green on green,” or just the weeds near the crop, said Serrat.

Bilberry tapped into what’s known as INT8 weight quantization, which enables more efficient application of deep learning models, particularly helpful for compact embedded systems in which memory and power restraints rule. This allowed them to harness 8-bit integers instead of floating-point numbers, and moving to integer math in place of floating-point helps reduce memory and computing usage as well as application latency.

It was early days for such AI applications, and people said it couldn’t be done. But farmers they spoke with wanted it.

Site-specific weed management (SSWM) refers to a spatially variable weed management strategy to minimize the use of herbicides [4]. However, the main technical challenge of SSWM implementation lies in developing a reliable and accurate weed detection system under field conditions [5]. As a result, various automated weed monitoring approaches are being developed based on unmanned aerial vehicle or on-ground platforms [6,7,8]. Among them, image-based methods integrating machine learning algorithms are considered a promising approach for crop/weed classification, detection and segmentation. Previous studies [7] utilized features like shape, texture and colour features with a random forest classifier for weed classification. Others, such as Ahmad el al [9] developed a real-time selective herbicide sprayer system to discriminate two weed species based on visual features and an AdaBoost classifier. Spectral features from multispectral or hyperspectral images could also be exploited for weed recognition [10, 11]. Although the works mentioned above show good results on weed/crop segmentation, classification and detection, challenges such as plant species variations, growth differences, foliage occlusions and interference from changing outdoor conditions still need to be further overcome in order to develop a real-time and robust model in agricultural fields.

Sugar beet (Beta vulgaris ssp. vulgaris var. altissima) is very vulnerable to weed competition due to its slow growth and low competitive ability at the beginning of vegetation [1]. The yield loss caused by weed competition can be significant. Therefore, effective weed management in early stages is critical, and essential if a high yield is to be achieved. In modern agriculture, herbicide is widely used to control weeds in crop fields [2]. Weeds are typically controlled by spraying chemicals uniformly across the whole field. However, the overuse of chemicals in this approach has increased the cost of crop protection and promoted the evolution of herbicide-resistant weed populations in crop fields [3], which is a hindrance to sustainable agriculture development.


Deep learning, a subset of machine learning, enables learning of hierarchical representations and the discovery of potentially complex patterns from large data sets [12]. It has shown impressive advancements on various problems in natural language processing and computer vision, and the performance of deep convolutional neural networks (CNNs) on image classification, segmentation and detection are of particular note. Deep learning in the agriculture domain is also a promising technique with growing popularity. Kamilaris et al. [13] concluded that more than 40 studies have applied deep learning to various agricultural problems like plant disease and pest recognition [14, 15], crop planning [16] and plant stress phenotyping [17]. Pound et al. [18] demonstrated that using deep learning can achieve state-of-the-art results (> 97% accuracy) for plant root and shoot identification and localization. Polder et al. [19] adapted an fully convolutional neural network (FCN) for potato virus Y detection based on field hyperspectral images. Specifically, for crop/weed detection and segmentation, Sa et al. [20, 21] developed WeedNet and WeedMap architectures to analyse aerial images from an unmanned aerial vehicle (UAV) platform. Lottes et al. [8, 22] also did relevant studies on weed/crop segmentation in field images (RGB + NIR) obtained from the BoniRob, an autonomous field robot platform. All these studies have demonstrated the effectiveness of deep learning, with very good results provided.

Convolvulus sepium (hedge bindweed) detection in sugar beet fields remains a challenging problem due to variation in appearance of plants, illumination changes, foliage occlusions, and different growth stages under field conditions. Current approaches for weed and crop recognition, segmentation and detection rely predominantly on conventional machine-learning techniques that require a large set of hand-crafted features for modelling. These might fail to generalize over different fields and environments.

The developed model has the potential to be deployed on an embedded mobile platform like the Jetson TX for online weed detection and management due to its high-speed inference. It is recommendable to use synthetic images and empirical field images together in training stage to improve the performance of models.