Search

During recent years, with the increase of production in agriculture, the need for more precise tools and practices has increased. One of those practices is the estimation of the fruit number in the tree. Computer vision techniques such as histogram of oriented gradients and edge/color detection have been used to extract features thus recognizing fruit based on shape and color. Existing methods usually rely heavily on computing multiple image features, making the whole system complex and computationally expensive. In this paper we compare those classical detection algorithms to new state-of-the-art convolution neural networks. Specifically, we compare two types of algorithms for apple detection in the tree. The first approach refereed as hard-coded uses commonly feature extraction filters (edge detector, color filtering, corners). On the other side are techniques using CNNs convolution neural networks like (residual networks, sliding window, regional dividers). More than thousand images of apple trees were taken during the season from flowering time to harvest. Same pictures have been processed through both techniques and based on results and the trade-offs of both techniques have been compared. For hard-coded algorithms, with few pictures we were able to see the performance of algorithm, while with CNNs, huge number of labeled pictures were needed for the algorithm to be more than 50% accurate. However, when a different picture from another date or completely new cultivar was used, the hard-coded algorithm failed to detect thus had to be rewritten to accommodate new changes. In other hand CNNs were very flexible and were able to detect apples even though the picture taken-date was changed or picture from another cultivar was used.

Wastewater may represent an alternative source for irrigation and mineral nutrients in intensive agriculture, offering potential agronomical and environmental advantages. This work investigates the effect of STW (secondary treated wastewater) used for irrigation, on the nutritional and physiological response of 3-year-old nectarine trees. To this end, trees ('Big Top'/'GF 677') were individually grown on 40-L pots filled with a sandy-loamy soil and drip irrigated with: a) Tap water (U) (unfertilized trees); b) Tap water (M) (mineral fertilized trees) and c) Secondary treated wastewater (W) (trees did not receive mineral fertilizers). Each treatment was applied to five individual trees. Regardless of the water source, trees received 360 L tree‑1 season‑1 and only M-trees received 14.2, 2.35, 8.96, and 0.72 g tree‑1 season‑1 of N, P, K and Mg, respectively, from commercial fertilizers throughout the season. Shoot length and photosynthetic daily assimilation rates were promoted by STW, compared to U trees, although M trees showed the highest values. This response is likely related to the amount of nutrients supplied to the trees along the season. Although STW provided a “fertigation-like” effect, results suggest that this strategy did not completely fulfill the tree nutrient demand. On the other hand, the STW recycling as irrigation water was not detrimental to plant growth. Treatments affected mainly leaf rather than fruit mineral concentration. Mineral concentration resulted mostly in the optimal range for all the treatments, except the U, which showed nutritional deficiencies. Heavy metal concentration both in leaves and fruit tissues was unaffected by treatments, with concentrations within international limits imposed for the human consumption. Results indicate how STW may be conveniently recycled as water source in the irrigation strategies of perennial species grown in temperate environments although this strategy may only contribute to partial fulfilment of plant nutrient requirements.