This study presents an automated method for detecting and measuring the apex head thickness of tomato plants, a critical phenotypic trait associated with plant health, fruit development, and yield forecasting. Due to the apex's sensitivity to physical contact, non-invasive monitoring is essential. This paper addresses the demand for automated, contactless systems among Dutch growers. Our approach integrates deep learning models (YOLO and Faster RCNN) with RGB-D camera imaging to enable accurate, scalable, and non-invasive measurement in greenhouse environments. A dataset of 600 RGB-D images captured in a controlled greenhouse, was fully preprocessed, annotated, and augmented for optimal training. Experimental results show that YOLOv8n achieved superior performance with a precision of 91.2 %, recall of 86.7 %, and an Intersection over Union (IoU) score of 89.4 %. Other models, such as YOLOv9t, YOLOv10n, YOLOv11n, and Faster RCNN, demonstrated lower precision scores of 83.6 %, 74.6 %, 75.4 %, and 78 %, respectively. Their IoU scores were also lower, indicating less reliable detection. This research establishes a robust, real-time method for precision agriculture through automated apex head thickness measurement.
DOCUMENT
Control of plant growth is an important aspect of crop productivity and yield in agriculture. Overexpression of the At CHR12/ 23 genes in Arabidopsis thaliana reduced growth habit without other morphological changes. These two genes encode Snf2 chromatin remodelling ATPases. Here, we translate this approach to the horticultural crop tomato ( Solanum lycopersicum). We identified and cloned the single tomato ortholog of the two Arabidopsis Snf2 genes, designated Sl CHR1. Transgenic tomato plants (cv. Micro-Tom) that constitutively overexpress the coding sequence of Sl CHR1 show reduced growth in all developmental stages of tomato. This confirms that Sl CHR1 combines the functions of both Arabidopsis genes in tomato. Compared to the wild type, the transgenic seedlings of tomato have significantly shorter roots, hypocotyls and reduced cotyledon size. Transgenic plants have a much more compact growth habit with markedly reduced plant height, severely compacted reproductive structures with smaller flowers and smaller fruits. The results indicate that either GMO-based or non- GMO-based approaches to modulate the expression of chromatin remodelling ATPase genes could develop into methods to control plant growth, for example to replace the use of chemical growth retardants. This approach is likely to be applicable and attractive for any crop for which growth habit reduction has added value.
DOCUMENT
Consumers expect product availability as well as product quality and safety in retail outlets. When designing or re-designing fruit and vegetables supply chain networks one has to take these demands into consideration next to traditional efficiency and responsiveness requirements. In food science literature, much attention has been paid to the development of Time-Temperature Indicators to monitor individually the temperature conditions of food products throughout distribution as well as quality decay models that are able to predict product quality based upon this information. This chapter discusses opportunities to improve the design and management of fruit and vegetables supply chain networks. If product quality in each step of the supply chain can be predicted in advance, good flows can be controlled in a pro-active manner and better chain designs can be established resulting in higher product availability, higher product quality, and less product losses in retail. This chapter works towards a preliminary diagnostic instrument, which can be used to assess supply chain networks on QCL (Quality Controlled Logistics). Findings of two exploratory case studies, one on the tomato chain and one on the mango chain, are presented to illustrate the value of this concept. Results show the opportunities and bottlenecks for quality controlled logistics depend on product—(e.g. variability in quality), process—(e.g. ability to use containers and sort on quality), network- (e.g. current level of cooperation), and market characteristics (e.g. higher prices for better products).
DOCUMENT
Tomato varieties used at present for commercial production in Dutch glasshouses have a high density of glandular trichomes on the stem, but a very low density on the leaves. The two-spotted spider mite, Tetranychus urticae Koch, and the predatory mite, Phytoseiulus persimilis Athias-Henriot, usually disperse from leaf to leaf via the stem, thereby incurring high risks of entrapment (and death) in the exudate of the glandular trichomes. These risks have been quantified on the tomato cv. 'Turbo' and an accession of Lycopersicon peruvianum almost free of glandular trichomes. The possible consequences for biological control are discussed and new perspectives for predator release strategies and for plant breeding are considered. © 1987 Elsevier Science Publishers B.V.
DOCUMENT
It has been shown that the identification of many foods including vegetables based on flavour cues is often difficult. The effect of providing texture cues in addition to flavour cues on the identification of foods and the effect of providing taste cues only on the identification of foods have not been studied. The aim of this study was to assess the role of smell, taste, flavour and texture cues in the identification of ten vegetables commonly consumed in The Netherlands (broccoli, cauliflower, French bean, leek, bell pepper, carrot, cucumber, iceberg lettuce, onion and tomato). Subjects (n ¼ 194) were randomly assigned to one smell (orthonasal), flavour (taste and smell) and flavour-texture (taste, smell and texture). Blindfolded subjects were asked to identify the vegetable from a list of 24 vegetables. Identification was the highest in the flavour-texture condition (87.5%). Identification was significantly lower in the flavour condition (62.8%). Identification was the lowest when only taste cues (38.3%) or only smell cues (39.4%) were provided. For four raw vegetables (carrot, cucumber, onion and tomato) providing texture cues in addition to flavour cues did not significantly change identification suggesting that flavour cues were sufficient to identify these vegetables. Identification frequency increased for all vegetables when perceived intensity of the smell, taste or flavour cue increased. We conclude that providing flavour cues (taste and smell) increases identification compared to only taste or only smell cues, combined flavour and texture cues are needed for the identification of many vegetables commonly consumed in The Netherlands.
DOCUMENT
Western-European consumers have become not only more demanding on product availability in retail outlets but also on other food attributes such as quality, integrity, and safety. When (re)designing food supply-chain networks, from a logistics point of view, one has to consider these demands next to traditional efficiency and responsiveness requirements. The concept ‘quality controlled logistics’ (QCL) hypothesizes that if product quality in each step of the supply chain can be predicted in advance, goods flows can be controlled in a pro-active manner and better chain designs can be established resulting in higher product availability, constant quality, and less product losses. The paper discusses opportunities of using real-time product quality information for improvement of the design and management of ‘AgriFood Supply Chain Networks’, and presents a preliminary diagnostic instrument for assessment of ‘critical quality’ and ‘logistics control’ points in the supply chain network. Results of a tomato-chain case illustrate the added value of the QCL concept for identifying improvement opportunities in the supply chain as to increase both product availability and quality. Future research aims for the further development of the diagnostic instrument and the quantification of costs and benefits of QCL scenarios.
DOCUMENT
Measuring plant health and status is key for growers in the Dutch greenhouse horticulture industry to create optimal conditions for plant growth and predictability and optimization of yield with minimal energy cost. Within the ‘Gewasgroei Goed Gemeten’ project led by The Hague University of Applied Sciences (project leader dr. John Bolte), plant data plays a key role. The consortium of researchers and entrepreneurs aims to pave the way towards large-scale application of sensor technology to record plant growth. Such a large-scale application asks for accurate, but low-cost sensors to be developed. Results of this project’s research and development, together with suppliers, growers and breeders, will advance the technology for Dutch horticulture and abroad, where there is a growing demand for Dutch knowledge and expertise.
DOCUMENT
Bitterness has been suggested to be the main reason for the limited palatability of several vegetables. Vegetable acceptance has been associated with preparation method. However, the taste intensity of a variety of vegetables prepared by differentmethods has not been studied yet. The objective of this study is to assess the intensity of the five basic tastes and fattiness of ten vegetables commonly consumed in the Netherlands prepared by different methods using the modified Spectrum method. Intensities of sweetness, sourness, bitterness, umami, saltiness and fattiness were assessed for ten vegetables (cauliflower, broccoli, leek, carrot, onion, red bell pepper, French beans, tomato, cucumber and iceberg lettuce) by a panel (n = 9) trained in a modified Spectrum method. Each vegetable was assessed prepared by different methods (raw, cooked, mashed and as a cold pressed juice). Spectrum based reference solutions were available with fixed reference points at 13.3 mm (R1), 33.3mm(R2) and 66.7mm(R3) for each tastemodality on a 100mmline scale. For saltiness, R1 and R3 differed (16.7 mm and 56.7 mm). Mean intensities of all taste modalities and fattiness for all vegetables were mostly below R1 (13.3 mm). Significant differences (p b 0.05) within vegetables between preparation methods were found. Sweetness was the most intensive taste, followed by sourness, bitterness, fattiness, umami and saltiness.In conclusion, all ten vegetables prepared by different methods showed low mean intensities of all taste modalities and fattiness. Preparation method affected taste and fattiness intensity and the effect differed by vegetable type.
DOCUMENT
Semi-closed greenhouses have been developed in which window ventilation is minimized due to active cooling, enabling enhanced CO2 concentrations at high irradiance. Cooled and dehumidified air is blown into the greenhouse from below or above the canopy. Cooling below the canopy may induce vertical temperature gradients along the length of the plants. Our first aim was to analyze the effect of the positioning of the inlet of cooled and dehumidified air on the magnitudes of vertical temperature and VPD gradients in the semi-closed greenhouses. The second aim was to investigate the effects of vertical temperature gradients on assimilate production, partitioning, and fruit growth. Tomato crops were grown year-round in four semiclosed greenhouses with cooled and dehumidified air blown into the greenhouses from below or above the crop. Cooling below the canopy induced vertical temperature and VPD gradients. The temperature at the top of the canopy was over 5°C higher than at the bottom, when outside solar radiation was high (solar radiation >250 J cm-2 h-1). Total dry matter production was not affected by the location of the cooling (4.64 and 4.80 kg m-2 with cooling from above and from below, respectively). Percentage dry matter partitioning to the fruits was 74% in both treatments. Average over the whole growing season the fresh fruit weight of the harvested fruits was not affected by the location of cooling (118 vs 112 g fruit-1). However, during summer period the average fresh fruit weight of the harvested fruits in the greenhouse with cooling from below was higher than in the greenhouse with cooling from above (124 vs 115 g fruit-1).
DOCUMENT
A (semi-)closed greenhouse is a novel greenhouse with an active cooling system and temporary heat storage in an aquifer. Air is cooled, heated and dehumidified by air treatment units. Climate in (semi-)closed greenhouses differs from that of conventional open greenhouses. The aims of our research were first, to analyze the effect of active cooling on greenhouse climate, in terms of stability, gradient and average levels; second, to determine crop growth and production in closed and semi-closed greenhouses. An experiment with tomato crop was conducted from December 2007 until November 2008 in a closed greenhouse with 700 W m-2 cooling capacity, two semi-closed greenhouses with 350 and 150 W m-2 cooling capacity, respectively, and an open greenhouse. The higher the cooling capacity, the more independent the greenhouse climate was of the outside climate. As the cooling ducts were placed underneath the plants, cooling led to a remarkable vertical temperature gradient. Under sunny conditions temperature could be 5°C higher at the top than at the bottom of the canopy in the closed greenhouse. Cumulative production in the semi-closed greenhouses with 350 and 150 W m-2 cooling capacity were 10% (61 kg m-2) and 6% (59 kg m-2) higher than that in the open greenhouse (55 kg m-2), respectively. Cumulative production in the closed greenhouse was 14% higher than in the open greenhouse in week 29 after planting but at the end of the experiment the cumulative increase was only 4% due to botrytis. Model calculations showed that the production increase in the closed and semi-closed greenhouses was explained by higher CO2 concentration.
LINK
