Agricultural Setup Research Articles

Real-Time Cow Detection and Identification Using Enhanced Particle Filter

In this paper, demonstration of how an individual cow can be tracked and identified in a herd of cows using an enhanced particle filter is presented. In a typical agricultural setup, it is not uncommon to witness cases of cow swapping and rustling. In the past, different methods were recorded in literatures for the monitoring of herds. However, advancement in technology has rendered those methods less effective, resulting to demand for continual improvement on the state-of-the-art methods for tracking individual cows. To achieve this, we employed off-the-shelf networks for end-to-end individual cow identification in up-to-down motionless imagery acquired from stationary camera. The dynamic trajectory of the herd was captured by a camera installed on a pole near a passageway through which the cows passed almost every day and the video processing system was employed for the processing of the herd’s trajectory. Report was made on the model initialisation, mean shift algorithm, particle-Kalman filter, and the target model is updated in order to overcome the change in the target object appearance over time. To our utmost knowledge, this work is the first to apply combination of mean-shift based tracker and particle-Kalman filter as enhanced particle filter to real-time cow detection and identification to curtail occlusion and non-linear tracking problem.

Heritage Tourism Trail Development in Kampung Luat, Perak: A Case Study

Kampung Luat situated in Lenggong Valley, Perak, is a well-known tourist destination due to its natural attraction, archaeological elements, promotion of rural agroindustry and home-based products, as well as unwavering and strong local community commitment. Distinct local characteristics, such as traditional culture, agricultural setup, countryside landscape, and simple lifestyles, offer a different experience for its visitors. The combination of these aspects provides a huge opportunity for tourism heritage trail development. As such, this study discusses the development of a heritage trail in Kampung Luat. The initiative was taken by a group of USM researchers, along with the cooperation from the local community. Observation and focus group discussion (FGD) techniques were adopted in this study. Several meetings were conducted and the development of Kampung Luat heritage trail was proposed, which covered seven stops in four hours, which involved 20-30 residents with different roles. This heritage trail was tested by 20 respondents. The findings showed that the visitors had placed a high value in the experience and enjoyed the different rural activities, apart from proposing several suggestions for trail improvement. Low level of community readiness, lack of facilities, and communication issues were their main concerns for trail improvement. These findings suggest the implementation of stringent and effective action taken by the federal and state governments, apart from including stakeholders to both coordinate and realise the heritage trail in future to increase the competitiveness at the Lenggong Valley as a tourism destination. Keywords: Heritage trail, trail development, case study, Kampung Luat, Lenggong Valley

A Hybrid Method for Smart Irrigation System

Internet of Things (IoT) is a boon to the technological developments during the past decade. Though the adoption of this technology in agriculture has gone up immensely in recent years, the implementation of the smart irrigation system remains its initial stage in this agricultural setup. The sprinkler or dripper irrigation methods are widely used in the smart irrigation environment. In this paper a hybrid method is proposed to select the irrigation method automatically based on the climate changes and soil moisture level. By enhancing this method using the rapid growing technologies and IoT enabled smart irrigation controllers, the agriculture sector will be improved over the foreseeable future.

Hollow fibre membrane-based liquid desiccant humidity control for controlled environment agriculture

Humidity control is an important factor affecting the overall sustainability, productivity, and energy efficiency of controlled environment agriculture. Liquid desiccants offer the potential for pinpoint control of humidity levels in controlled environments. In the present work, a dehumidification processes utilizing liquid desiccants pumped through the lumens of triple-bore PVDF hollow fibre membranes is implemented in a bench scale controlled environment agriculture system. Hydrophobic hollow fibre membranes were combined into an array and placed near the crops. Concentrated magnesium chloride liquid desiccant solution with a low vapour pressure was pumped through the hollow fibre lumens. The dehumidification permeance rate responded dynamically to the changing transpiration rate of the plants, as influenced by changes in environmental factors such as light, temperature, and vapour pressure. The dehumidification permeance rate increased from an average of 0.26–0.31 g m−2 h−1 Pa−1 as the velocity of the liquid desiccant through the hollow fibres increased from 0.023 to 0.081 m s−1. Humidity levels were targeted to be maintained within a range of 70–90% relative humidity at 23 °C. The membrane-based liquid desiccant system was demonstrated to successfully control humidity within a bench-scale controlled environment agricultural setup.

Field performance of terpene-producing Camelina sativa

Bioengineered lines of the low-input oil seed crop Camelina sativa (Camelina), augmented to accumulate the monoterpene (4S)-limonene, the sesquiterpene (+)-δ-cadinene, or the sesquiterpene (+)-5-epi-aristolochene in seed, were evaluated for two growing seasons under field conditions to determine performance of the introduced traits in an agricultural setup including the effects on overall plant fitness, and total seed yield. Field-grown Camelina plants were further compared to greenhouse-grown plants to evaluate commonalities and differences resulting from cultivation under either controlled or agriculturally relevant growth conditions. Morphological appearance and plant height differed marginally between transgenic and wild-type plants under both greenhouse and field conditions, indicating low impact of the terpene production traits toward overall plant fitness. Total seed yield, however, was independent of the growth conditions and was reduced in Camelina lines producing (4S)-limonene by 48% on average and by 30% on average for (+)-5-epi-aristolochene producing lines. Conversely, (+)-δ-cadinene producing Camelina seed yields remained wild-type equivalent. Additional investigations included seed terpene accumulation, seed oil amount, and seed fatty acid composition. Terpene accumulation was reduced up to 22% for field-grown plants as compared to greenhouse-grown plants. Seed oil amounts were similar under greenhouse and field conditions but were consistently lowered by 2–5% for terpene producing lines. Similarly, seed oil composition remained stable under both field and greenhouse conditions, but generally favored a more energy dense phenotype in terpene producing Camelina lines. Lastly, outcrossing of transgenic traits to adjacent wild-type Camelina plants was observed under field but not greenhouse conditions.

Grain storage losses in the traditional tribal settlements of Biligirirangana Hills, Karnataka, India

The forest dwelling tribal Soligas who reside at Biligirirangana Hills cultivate more than 30 different crops including pulses, cereals, millets and vegetable crops as a part of subsistence agriculture. They store more than 80% of their produce in their households for consumption. The present study examines the grain storage practices followed by Soligas and the extent of losses incurred by them, in a traditional agricultural setup. In all, 13 different storage structures used by Soligas were recorded. These included both traditional and modern structures. Among these, plastic oven sac was being used most widely, while Thenemane used for storing maize cobs was the least used structure by the Soligas. An evaluation of these storage structures for safe storage of grains revealed that, none of the traditional storage structures were found to be suitable for grain storage, as they had one or the other disadvantages like, not being moisture or insect or rodent proof. However, the modern structures like, the plastic bins were moisture and rodent proof, but they failed to provide protection against insects. Soligas adopted 10 different grain protection methods for safe storage of grains. Despite their use, the presence of insect infestation ranged from 32.14 to 56.41%. Callosobruchus theobromae was the most common stored grain insect found infesting fieldbean (Dolichos bean) that was stored in most of the settlements, while Tribolium castaneum was the rarest, found infesting only split pigeon pea (Cajanus cajana). The extent of grain damage ranged from 10 to 100% in the samples collected.

Sparse unmixing via variable splitting and augmented Lagrangian for vegetation and urban area classification using Landsat data

Abstract. In this paper, we explore the possibility of sparse regression, a new direction in unmixing, for vegetation and urban area classification. SUnSAL (Sparse unmixing via variable splitting and augmented Lagrangian) in both unconstrained and constrained forms (with the abundance non-negativity and abundance sum-to-one constraints) were used with a set of global endmembers (substrate, vegetation and dark objects) to unmix a set of computer simulated noise-free and noisy data (with Gaussian noise of different signal-to-noise ratio) in order to judge the robustness of the algorithm. The error in the fractional estimate was examined for varying noise power (variance): 2, 4, 8, 16, 32, 64, 128 and 256. In the second set of experiments, a spectrally diverse collection of 11 scenes of Level 1 terrain corrected, cloud free Landsat-5 TM data representing an agricultural setup in Fresno, California, USA were used. The corresponding ground data for validation were collected on the same days of satellite overpass. Finally in the third set of experiments, a clear sky Landsat-5 TM data for an area near the Golden Gate Bridge, San Francisco (an urbanized landscape), California, USA were used to assess the algorithm. The fractional estimates of the 30 m Landsat-5 TM data were compared with the fractional estimates of a high-resolution World View-2 data (2 m spatial resolution) obtained using a fully constrained least squares algorithm. The results were evaluated using descriptive statistics, correlation coefficient, RMSE, probability of success and bivariate distribution function, which showed that constrained model was better than unconstrained form.

Development of a Wireless Sensor Network for Monitoring Environmental Condition on a Farmland

In recent time, the wireless sensor network technology has found its implementation in precision agriculture as a result of the need for high productivity. This paper focuses on the development of a wireless sensor network on agricultural environment to monitor environmental conditions and deduce the appropriate environmental parameters required for the high yield of crop production on a given farmland. The developed wireless sensor network is built around sensor nodes and a master microcontroller (PI16F648A) that takes in the data sent from the nodes for upload into a personal computer (PC). Each node has sensors to monitor environmental conditions such as temperature, relative humidity and light intensity which are important environmental factors in an agricultural set-up. The DHT11 sensor is used to sense and provide calibrated digital outputs for the measured temperature and relative humidity while a calibrated light dependent resistor (LDR) is configured to the light intensity sensor unit. The outputs from these sensors are processed by the microcontroller and sent wirelessly, using low-power radio frequency transceivers, to a remote master controller for storage. The deployment of the developed wireless sensor network on a named farmland shows that the aforementioned could be efficiently utilized to provide an up-todate and accurate measurement of agricultural environmental parameters necessary for plant protection and sustainable crop production. Thus, the developed wireless sensor network replaces the traditional method of predicting environmental parameters required on a given farmland.

Interruption of microbial cycles in farm animals from farm to table

The fact that only slight problems are posed by Salmonella, Campylobacter and Escherichia coli O157 in mammalian farm animals in Norway, is undoubtedly due in large degree to the agricultural set-up with small farms and small herds, allowing a good overview of the situation at any time. Other factors are the very limited import of breeding animals and food products of animal origin, microbiological control of animal feed, and favourable geographical and climatic conditions. However, the Norwegian meat industry (including abattoirs) has continuing problems with Yersinia enterocolitica O:3 in pigs and pig meat, and in some cases with Listeria monocytogenes in cold cuts and Toxoplasma gondii in sheep meat (lamb). These three agents are therefore used to illustrate appropriate measures to be taken at the herd level on the farm, in abattoirs and in the meat processing industry.