Bruno Bernardi

Computer vision for automatic quality inspection of dried figs (Ficus carica L.) in real-time

Dried fig skin colour was assessed comparing image analysis and colourimetry.PCA and PLS-DA distinguished between high quality figs and deteriorated ones.A system based on computer vision for sorting of figs in real-time was developed.The browning index and X colour coordinate guaranteed an accurate sorting. This work reports the development of automated systems based on computer vision to improve the quality control and sorting of dried figs of Cosenza (protected denomination of origin) focusing on two research issues. The first was based on qualitative discrimination of figs through colour assessment comparing the analysis of colour images obtained using a digital camera with those obtained according to conventional instrumental methods, i.e. colourimetry currently done in laboratories. Data were expressed in terms of CIE XYZ, CIELAB and HunterLab colour spaces, as well as the browning index measurement of each fruit, and then, analysed using PCA and PLS-DA based methods. The results showed that both chroma meter and image analysis allowed a complete distinction between high quality and deteriorated figs, according to colour attributes. The second research issue had the purpose of developing image processing algorithms to achieve real-time sorting of figs using an experimental prototype based on machine vision, simulating an industrial application. An extremely high 99.5% of deteriorated figs were classified correctly as well as 89.0% of light coloured good quality figs A lower percentage was obtained for dark good quality figs but results were acceptable since the most of the confusion was among the two classes of good product.

Occupational risks related to vibrations using a brush cutter for green area management

INTRODUCTION Weed control is one of the most important issues in the maintenance sectors of both agriculture and green areas. Small tools are employed for controlling grass and other growths on steep verges and river banks. This leads the operators being exposed to many risks among which vibration is one. The purpose of this study is to measure and evaluate hand-arm vibration and to verify the daily exposure to which workers are often subjected while weeding. MATERIAL AND METHODS Two cutting heads, a brush knife and a mowing head were compared. Both were mounted on the same cow-horn brush cutter. The vibration total value was expressed as the root-mean-square (rms) of three component values according to the axes X, Y and Z. The signal was frequency weighted using the weighting curve Wh, as described in the ISO 5349-1 (2001) standard. In addition, the daily vibration exposure was calculated and compared with the thresholds set by EU Directive 2002/44/EC (2005). RESULTS The obtained results showed that the exposure action value (EAV) of 2.5 ms-2 was exceeded while using both cutting heads. The exposure limit value (ELV) using the brush knife also exceeded 5 ms-2. CONCLUSIONS The results highlighted important aspects in terms of exposure values that should be considered with the view of preventing the risk of Hand-Arm Vibration Syndrome (HAVS) to which the operators who frequently use these tools are exposed. Specific measures should therefore be taken to protect the exposed workers.

The assessment of hazelnut mechanical harvesting productivity

Hazelnut cultivation represents a new opportunity for Calabrian mountainous and sloping areas (Southern Italy), where no alternative fruit crops, except forestry, could be settled. In this Region, hazelnut production doubled during the last fifty years, inciting the farmers to introduce mechanization in cropping practices such as harvesting in order to increase productivity and decrease production costs. Indeed, harvesting is currently one of the most expensive processes of the productive cycle, moreover to be time consuming if carried out manually. Mechanization degree depends significantly on the terrain topography: in sloping areas, rakes are often associated to aspirating machines to harvest the fallen fruit, while the employment of harvesting machines from the ground prevails in flat areas. In this context, the present paper aims to assess technical and economic aspects of harvesting operation, using a harvester from the ground model ‘Jolly 2800’ (GF s.r.l., Italy). Particularly, for technical purposes data about operational working time as well as working productivity were collected according to CIOSTA requirements, in two harvesting sites, whereas, for mechanical harvesting economic evaluation, an estimation model was applied to calculate machinery cost per hour. Moreover, the cost per kg of hazelnut in shell and the average cost per hectare were estimated also. The obtained results show a working productivity of 0.065 ha h op in the first harvesting site, while it was equal to 0.022 ha h op in the second one. Concerning the average cost per hectare, the second harvesting site showed the worst economic performances, with 550.76 € ha against 182.54 € ha obtained in the first one.

Assessment of the Ripening of Olives Using Computer Vision

Assessment of the Ripening of Olives Using Computer Vision Souraya Benalia, Bruno Bernardi*, José Blasco, Antonio Fazari, Giuseppe Zimbalatti a Department of AGRARIA, University Mediterranea of Reggio Calabria, Loc. Feo di Vito, 89122 Reggio Calabria, Italy b Agricultural Engineering Center, Instituto Valenciano de Investigaciones Agrarias (IVIA), CV-315, Km. 10,7 – 46113 Moncada (Valencia), Spain bruno.bernardi@unirc.it